US20020054083A1 - Media browser using multimodal analysis - Google Patents

Media browser using multimodal analysis Download PDF

Info

Publication number
US20020054083A1
US20020054083A1 US09/934,486 US93448601A US2002054083A1 US 20020054083 A1 US20020054083 A1 US 20020054083A1 US 93448601 A US93448601 A US 93448601A US 2002054083 A1 US2002054083 A1 US 2002054083A1
Authority
US
United States
Prior art keywords
feature
media file
media
confidence score
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US09/934,486
Inventor
John Boreczky
Andreas Girgensohn
Jonathan Foote
Original Assignee
Xerox Corporation And Fuji Xerox Co.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xerox Corporation And Fuji Xerox Co. filed Critical Xerox Corporation And Fuji Xerox Co.
Priority to US09/934,486 priority Critical patent/US20020054083A1/en
Publication of US20020054083A1 publication Critical patent/US20020054083A1/en
Assigned to BANK ONE, NA, AS ADMINISTRATIVE AGENT reassignment BANK ONE, NA, AS ADMINISTRATIVE AGENT SECURITY AGREEMENT Assignors: XEROX CORPORATION
Assigned to NATIONAL INSTITUTES OF HEALTH (NIH), U.S. DEPT. OF HEALTH AND HUMAN SERVICES (DHHS), U.S. GOVERNMENT reassignment NATIONAL INSTITUTES OF HEALTH (NIH), U.S. DEPT. OF HEALTH AND HUMAN SERVICES (DHHS), U.S. GOVERNMENT CONFIRMATORY LICENSE (SEE DOCUMENT FOR DETAILS). Assignors: SALK INSTITUTE FOR BIOLOGICAL STUDIES
Assigned to XEROX CORPORATION reassignment XEROX CORPORATION RELEASE BY SECURED PARTY (SEE DOCUMENT FOR DETAILS). Assignors: JPMORGAN CHASE BANK, N.A. AS SUCCESSOR-IN-INTEREST ADMINISTRATIVE AGENT AND COLLATERAL AGENT TO BANK ONE, N.A.
Abandoned legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/74Browsing; Visualisation therefor
    • G06F16/745Browsing; Visualisation therefor the internal structure of a single video sequence
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7834Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using audio features
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7847Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/85Assembly of content; Generation of multimedia applications
    • H04N21/854Content authoring
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99941Database schema or data structure
    • Y10S707/99944Object-oriented database structure
    • Y10S707/99945Object-oriented database structure processing
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99941Database schema or data structure
    • Y10S707/99948Application of database or data structure, e.g. distributed, multimedia, or image
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S715/00Data processing: presentation processing of document, operator interface processing, and screen saver display processing
    • Y10S715/961Operator interface with visual structure or function dictated by intended use
    • Y10S715/965Operator interface with visual structure or function dictated by intended use for process control and configuration
    • Y10S715/966Computer process, e.g. operation of computer
    • Y10S715/968Computer process, e.g. operation of computer interface for database querying and retrieval

Definitions

  • This invention relates to a method and apparatus for reviewing an aural and/or visual and/or other representation of a media file. Specifically, the invention relates to using media content features to allow a user to more easily review a media file.
  • Text documents often have many cues, such as headings, paragraphs, punctuation, etc., that allow a reader to quickly determine the beginning and end of different sections of the document and to aid the reader in finding areas of interest.
  • video and audio browsing systems typically do not provide information to the user regarding simple features, like section beginning and end points, much less more complicated information, like the name of the speaker on a video clip.
  • Such browsing systems typically offer only standard “VCR-type” playback control options, like play, stop, rewind, and fast forward. As anyone who has tried to find a specific video clip on a conventional video tape using a standard VCR will understand, it is often difficult to locate portions of interest in a video using the standard playback controls.
  • media or media file is used to represent any data stream that contains information regarding video or other image information, audio information, text information and/or other information.
  • a feature of a media file is a property of the video, audio and/or text information in the media file, such as video or audio format, or information relating to the content of the media file, such as the identity of a speaker depicted in a video sequence, occurrences of applause, video shot boundaries, or motion depicted in a video sequence.
  • video or audio format such as video or audio format
  • information relating to the content of the media file such as the identity of a speaker depicted in a video sequence, occurrences of applause, video shot boundaries, or motion depicted in a video sequence.
  • Providing feature information in a media browsing system can be very useful for a user when identifying areas of interest in a media file, controlling media playback, editing a media file, or performing other operations with a media file. For example, graphically identifying areas in a media file where a particular speaker is shown on a video clip can allow a user to quickly determine and playback those portions that contain the speaker.
  • Providing feature information to the user based on automatically identified features also eliminates the need for a user to manually index or otherwise mark significant portions of the media file for later retrieval.
  • the invention can use existing methods for automatically identifying features in a media file to generate and provide feature information to a user to aid the user in browsing the media file.
  • the invention provides a media browser that uses media feature information as an aid in navigating, selecting, editing, and/or annotating a media file.
  • media features are selected by a user.
  • media browsing functions such as play, rewind, stop, fast-forward, index, automatic slide show, and automatic preview, are controlled based on feature information.
  • feature information for a selected feature is mapped to a corresponding confidence score.
  • the media browser includes a feature indicator that provides information related to a corresponding selected feature based on a corresponding confidence score.
  • a feature indicator combines at least two confidence scores and provides information based on the combination.
  • a feature indicator provides information related to a confidence score based on a value of another confidence score.
  • the invention also provides a method for browsing a media file.
  • a feature of the media file being browsed is selected and information related to a confidence score for at least one selected feature is provided.
  • the confidence score relates to the existence of a corresponding selected feature in the media file. Based on the information related to the confidence score, a portion of the media file is selected.
  • a metadata value representing a time-wise evaluation of a feature in the media file is mapped to a corresponding confidence score.
  • mapping of a metadata value to a corresponding confidence score is non-linear.
  • mapping of a metadata value to a confidence score is dependent on a user-defined control value or values.
  • FIG. 1 is an example screen display for a graphical user interface in accordance with the invention
  • FIG. 2 shows example metadata values, corresponding confidence score information, and an example graphical depiction of corresponding feature information
  • FIGS. 3 - 9 show different ways of graphically depicting information related to a feature in a media file
  • FIG. 10 is an example screen display depicting how features can be combined and corresponding combined feature information can be shown
  • FIG. 11 is an example screen display depicting how display of feature information relating to a corresponding feature can be conditioned on another feature
  • FIG. 12 is a flow chart explaining basic steps of a preferred method for browsing a media file
  • FIG. 13 is a schematic block diagram of a preferred media browser in accordance with invention.
  • FIG. 14 is a flow chart of steps of a preferred method for selecting a media file to be browsed
  • FIG. 15 is a preferred media selection screen
  • FIG. 16 is a flow chart of steps of a preferred method for mapping feature metadata to a corresponding confidence score
  • FIG. 17 is a flow chart of steps of a preferred method for processing confidence scores and providing information related to the confidence scores
  • FIG. 18 is a flow chart of steps of a preferred method for controlling playback functions based on a selected feature.
  • FIG. 19 is a flow chart of steps of a preferred method for reviewing a media file based on selection of a confidence score indication.
  • browsing refers to any operation related to reviewing, manipulating, editing, selecting portions of, storing, transmitting, or other operations related to a media file.
  • a preferred embodiment of a graphical user interface for a media browser is described below having specific functions. In many cases, various functions of the media browser can be eliminated or altered, as desired. For example, information that is displayed graphically in the embodiment described below can be provided aurally or otherwise, as described more fully below.
  • a common video analysis technique is the detection of shot boundaries, which represent significant differences between consecutive video frames.
  • the difference between consecutive video frames can be determined based on statistical properties of the pixels in the frame images, histogram differences, compression algorithms, edge differences, or motion detection.
  • Application of one of several known techniques for detecting shot boundaries results in a series of time-varying metadata values that each represent a difference between consecutive video frames.
  • metadata regarding the shot boundary feature is determined, information can be provided to a user to aid the user in locating portions of interest in the media file, e.g., places in the media file where scene changes occur.
  • Metadata can be automatically generated
  • metadata can be input by a user or group of users. For example, a user could review a media file and identify sections of the media file where a particular speaker is featured, e.g., the speaker is either shown visually or is speaking. After identifying portions of the media file where a speaker is featured, the user can manually enter metadata that indicates the user's subjective evaluation of whether the speaker is present in the media file at each time-wise position in the media file. The user can enter the metadata continuously after viewing each video frame or listening to each predefined sub-portion of the media file. Alternately, the user could identify onoy those portions of the media file where the speaker is featured, and all other portions of the media file could be assigned metadata values that indicate that the speaker is not present in the media file.
  • FIG. 1 shows an example graphical user interface 10 in accordance with the invention.
  • the graphical user interface 10 is typically displayed on a video display, such as a computer monitor, but can be presented to a user on any other display device.
  • the interface 10 has a video display portion 1 in which a still video frame representation of an image contained in a media file can be presented. Video frames can also be displayed at any desired video frame rate, such as that performed on a standard computer monitor or television set. Audio representations of sound information contained in a media file can be presented to a user by a speaker (not shown). Alternately, visual representations of sound information, such as a waveform, can be presented on the graphical user interface 10 .
  • a playback control bar 2 contains playback controls that are used to control how a visual and/or aural representation of a media file is presented to a user.
  • the playback control bar 2 can include buttons for controls such as play, stop, rewind, fast forward, and forward and reverse index.
  • the playback controls shown in FIG. 1 are not intended to be an exhaustive representation of all of the different types of playback controls that can be provided.
  • controls can be provided to alter the effective frame rate at which a video display is generated or the speed at which a sound representation is played back.
  • a user activates controls on the playback control bar 2 by clicking a desired button with a mouse cursor.
  • Other methods for activating the controls can be used, such as individual keystrokes or combinations of keystrokes on a keyboard, selection of controls using a touch screen or light pen, or other selection device.
  • a timeline 3 includes a thumb 31 that indicates a current time-wise position in the media file.
  • the timeline 3 shown in FIG. 1 ranges from time 0:00 to time 47:38 and can be optionally zoomed in or out and panned using the timeline controls 32 .
  • the thumb 31 can be moved time-wise along the timeline 3 by using the left and right timeline controls 32 .
  • a user could select the thumb 31 using a mouse and move the thumb 31 to a desired position along the timeline 3 using the mouse.
  • By moving the thumb 31 time-wise along the timeline 3 a corresponding video and/or aural representation of the media file located at the time-wise position of the thumb 31 can be played back.
  • video frames or preselected keyframes at corresponding time-wise locations in the media file can be displayed in the video display portion 1 as the thumb 31 is moved.
  • video/aural playback could begin from a corresponding position in the media file after the thumb 31 is moved to a desired position and released.
  • a user can select a feature in the media file using a media feature selection 4 .
  • the feature selection 4 includes a scroll bar for navigating through a list of selectable features.
  • features in the feature selection 4 are selected by double clicking a desired feature with a mouse cursor.
  • a user could type in a selected feature using a keyboard or otherwise enter a selected feature, such as by speaking a selected feature, which is recognized by the browsing system using voice recognition techniques.
  • the features listed in the feature selection 4 are organized in alphabetical order or otherwise grouped logically. For example, video-related features are preferably grouped apart from audio-related features.
  • Selected features are displayed in selected feature windows 5 .
  • selected feature windows 5 In the example graphical user interface 10 of FIG. 1, three selected feature windows 5 - 1 , 5 - 2 , and 5 - 3 are shown. However, fewer or more selected feature windows 5 could be used.
  • Corresponding to each selected feature window 5 is a feature indication window 6 .
  • the feature indication window 6 preferably graphically indicates the time-wise presence or absence of a corresponding feature in the media file, but the feature indication window 6 could display other information related to the corresponding feature.
  • the feature indication window 6 - 3 graphically displays the time-wise presence of applause in the media file.
  • solid vertical lines displayed in a feature indication window 6 indicate a determination that the corresponding feature is likely present in the media file at the corresponding time-wise location in the media file.
  • other representations are possible, as discussed more fully below.
  • a feature summary bar 7 preferably graphically displays a summary of the selected features.
  • the feature summary bar 7 includes graphical icons 8 that each indicate, or represent, specific information.
  • the scissors icon 8 indicates the presence of a cut or shot detect in the media file.
  • the icons 8 can also indicate information related to two or more features. For example, a rectangular icon 8 containing a circle indicates a portion of the media file that contains an occurrence of applause followed shortly after a shot detect occurrence. This is only one example of the possible icons 8 that can be used to summarize selected features. Additional summary representations are discussed below.
  • Key playback buttons 9 are also provided for each of the selected features and for the feature summary bar 7 .
  • the key playback buttons 9 allow a user to select a feature that is used to control playback functions of the playback control bar 2 .
  • the play and/or index buttons in the playback control bar 2 could be controlled such that whenever the button is selected, portions of the media file containing the speaker MD are “jumped” to and played back. Other portions of the media file are skipped and not presented to the user.
  • the index buttons in the playback control bar 2 could be controlled such that whenever an index button is selected, a representation of the media file begins immediately before or after occurrences of applause in the media file.
  • the interface 10 also includes a confidence score value manipulation control 11 that allows a user to adjust confidence score values for corresponding features as desired.
  • a confidence score relates to a corresponding feature, is preferably determined using metadata for a corresponding feature, and preferably is used to generate the information displayed in the feature indication windows 6 .
  • automatically derived metadata is preferably mapped to a corresponding confidence score.
  • the confidence score is thus intended to convey to a user, in an understandable form, the probability of a feature's existence in the media file.
  • the metadata is mapped to a corresponding time-varying confidence score using some function that is based on prior knowledge about the metadata's reliability.
  • mapping of the metadata to a confidence score can be performed in a one-to-one relationship, where individual metadata data values are equal to corresponding confidence score values.
  • FIG. 2 shows an example of shot detect metadata derived from a media file containing video information.
  • the metadata values are represented graphically, and in this example, relatively larger metadata values represent relatively large differences between consecutive video frames at a corresponding time-wise position in the media file.
  • Metadata representing shot boundary values are mapped to a confidence score using a threshold. If a metadata value is above the threshold, the corresponding confidence score is assigned a value of one, indicating a relatively high probability that a video cut is present in the media file. If the metadata value is below the threshold, the corresponding confidence score is assigned a value of zero.
  • the threshold is adjusted automatically or by a user based on the reliability of the metadata.
  • the confidence scores for the shot detection feature can be depicted in a feature indication window 6 of a graphical user interface 10 as shown in FIG. 2. In this example, dark portions of the feature indication window 6 represent a confidence score of zero and light portions of the feature indication window 6 represent confidence score values of one.
  • the metadata values for a media feature can be mapped to a confidence score in many different ways.
  • the metadata values are preferably mapped to corresponding confidence score values using a function that is determined based on the feature corresponding to the metadata and the reliability of metadata.
  • Linear or non-linear mapping including normalization, thresholding and filtering, can be performed for numerical metadata.
  • non-numerical metadata such as text, closed captions (subtitles), or MIDI streams
  • metadata can be mapped to confidence score values using statistical or other mathematical methods.
  • the time-wise frequency of a word or set of words in a media data stream could be converted to a set of confidence score values where a relatively high confidence score value is assigned to a portion of the media file that contains relatively more occurrences of the word or set of words, and lower confidence scores are assigned to portions containing fewer occurrences of the word or set of words.
  • a lower dimensional confidence score can be computed.
  • a face recognition algorithm generates five numerical values for each face detected in a video frame: the coordinates of the upper left and lower right corners of the bounding rectangle of the candidate face, and how well the candidate matches the face template.
  • a confidence score for the face is preferably determined according to Equation 1:
  • CA is the area of the candidate face determined from the upper left and lower right comer coordinates
  • MFA is the maximum face area (a constant).
  • CA is preferably not larger than or constrained to be not larger than MFA.
  • mapping metadata values to confidence score values can be performed according to functions that are “learned” using techniques such as learning Bayesian networks. For example, a confidence score mapping system could “learn” that metadata determined for a particular feature is more or less reliable than originally anticipated, and adjust the mapping function, e.g., a mapping threshold, accordingly.
  • a confidence score mapping system could “learn” that metadata determined for a particular feature is more or less reliable than originally anticipated, and adjust the mapping function, e.g., a mapping threshold, accordingly.
  • Mapping of metadata values is also preferably controlled based on user control values.
  • a user can adjust a threshold value or other control values using the confidence score value manipulation control 11 in the graphical user interface 10 .
  • adjusting the sliders on the confidence score value manipulation control 11 can adjust the threshold value or values used to map the metadata to confidence scores.
  • the user can adjust the sensitivity of the mapping function to the metadata and customize the feature information displayed in the feature indicator windows 6 .
  • only one threshold is used and so only one slider need be displayed on the confidence score value manipulation control 11 .
  • more than one threshold can be used to map metadata to confidence scores and so an additional slider can be displayed.
  • the confidence score value manipulation control 11 can also be used to adjust mapping control values other than thresholds, such as filter coefficient values, or any other value used to change the way metadata is mapped to confidence score values.
  • the confidence score information is preferably provided to a user as an aid in browsing a media file as discussed above.
  • FIGS. 3 - 9 show additional examples of how confidence score information can be presented to a user. These examples are not intended to be exhaustive and other methods can be used to provide confidence score information.
  • confidence score information can be conveyed to stimulate human senses other than sight, including sound, touch (e.g., by activating a Braille touchpad) or smell.
  • FIGS. 3 - 6 involve a selected feature “speaker MD”.
  • This feature represents a speaker depicted and/or recorded in a media file where MD represents the speaker's initials.
  • metadata related to the speaker's identity can be generated using face recognition techniques, in the case where the speaker is identified “visually” or using speech recognition techniques, where the speaker is identified as having a particular speech pattern, for example.
  • the speaker's identity can also be verified manually by a user. For example, a user can review a media file and enter metadata directly into the system indicating whether a particular speaker is featured in the media file. The user can also enter metadata for other feature types, thereby eliminating a need to have the metadata determined automatically.
  • FIG. 3 shows an example feature indication window 6 containing icons 8 .
  • the icons 8 represent likely portions in a media file where the speaker MD either talks or is represented visually. In this example, portions where the speaker MD either talks or is represented visually are identified as those portions for which the confidence score exceeds a given threshold.
  • the icons 8 optionally contain a representation of speaker MD's face or is a thumbnail keyframe extracted from the media file at a corresponding point in the media file.
  • a representation of the media file at a point corresponding in time is presented to the user.
  • portions of the media file that most likely contain the speaker MD are indicated by shaded portions in the feature indication window 6 .
  • the shaded portions can include color.
  • speaker MD could be assigned the color green, and all green portions displayed in the feature indication window 6 indicate portions of the media file most likely containing the speaker MD.
  • the display is generated based on the corresponding confidence score, which may not always accurately indicate if the corresponding feature is present in the media file.
  • the metadata and corresponding confidence score represents a probability or “best guess” regarding whether the feature is present in the media file. This may be true even when a user enters the metadata into the system. For example, a user may not be certain that a particular person is speaking in a media file even though the user is very familiar with the person's voice.
  • the confidence score corresponding to speaker MD is displayed in the feature indication window 6 .
  • the metadata corresponding to speaker MD can be directly mapped on a one-to-one basis to the confidence score. That is, the metadata values are the same as the corresponding confidence score values.
  • the confidence score values may not always indicate that the speaker MD is either positively included or not included in the media file. Rather, the confidence score values can vary indicating an uncertainty regarding whether the corresponding feature is present in the media file. This uncertainty may be due to noise in the media data stream, two or more speakers speaking simultaneously, or that a portion of the speaker's face is partially obscured.
  • the confidence score values shown in FIG. 5 have been thresholded to generate the display in the feature indication window 6 .
  • any confidence score values that fall below the maximum value are clipped to the lowest possible value.
  • a user can vary the threshold values used to process the confidence score values to generate the feature indication using the confidence score value manipulation control 11 , or otherwise vary how the feature indication is presented based on the confidence score values.
  • FIGS. 7 - 9 relate to the display of confidence score information for a video cut feature in a media segment.
  • the confidence score values are shown without manipulation in the feature indication window 6 .
  • increasing confidence score values indicate higher probabilities that a video cut has been detected.
  • the video cut feature indication shown in the feature indication window 6 is generated based on integrating the confidence score values over time. This type of indication can be useful for determining the total number of video cuts in a media segment or in determining how much the video images change within the media segment.
  • the change in the integrated value is proportional to the fraction of total accumulated feature change in the media file.
  • FIG. 8 can vary in color as the curve represents an increase in value.
  • the curve could start as a blue color for relatively low values and gradually change to a red color for maximum integration values. That is, the curve could start as a blue color and as the curve increases in value, the curve gradually changes through various shades of purple of increasing red content.
  • FIG. 9 shows an alternate representation of the integrated confidence score value where the integrated value is represented only by a corresponding color change in the feature indication window 6 without display of the integration curve itself.
  • the change in color represents the total accumulated feature change in the media file.
  • the graphical user interface 10 preferably includes an option for combining features and displaying confidence score information based on the feature combination, as shown in FIG. 10.
  • the features “speaker MD” and “applause” are combined, and the corresponding feature indication window 6 indicates media portions where the speaker MD is depicted during applause. This type of combination can be useful to locate portions in a media file where a particular speaker begins and/or ends a presentation or has made a particularly interesting comment during a presentation.
  • FIG. 10 shows another combination of the features “silence” and “shot detect”.
  • the corresponding feature indication window 6 indicates portions in the media file where a shot detect and silence are simultaneously present. This combination can be useful to indicate the beginning or end of a desired portion in the media file.
  • the graphical user interface 10 includes a “Combine” button that a user can click to combine two or more features.
  • a user can define which features to combine by other methods.
  • confidence score information can be conditioned on other features.
  • confidence score information related to the feature “speaker MD” is displayed only when confidence score information indicates a relatively high probability that the speaker MD is shown in a video segment of the media file along with or within two minutes of applause in the soundtrack of the media file.
  • other feature combinations or conditions e.g., Boolean operators, can be used depending on the type of feature indication information needed for a specific task and the relevant features.
  • FIG. 12 is a flowchart of a preferred method for browsing a media file.
  • a user inputs a command indicating a desire to browse a media file.
  • the desired media file is retrieved.
  • the graphical user interface 10 is preferably displayed to the user, although other interfaces can be used.
  • the user preferably selects at least one feature of the media file.
  • confidence scores corresponding to the selected features are retrieved and/or generated.
  • metadata values for all of the selectable features are precomputed and stored with the media file so that metadata values need not be generated during a browsing session. However, the metadata values and corresponding confidence score values can be generated during a browsing session.
  • step S 60 feature indications related to the selected features are displayed to the user.
  • step S 70 the user enters commands to play back or otherwise manipulate the media file as desired. For example, a user can click on an icon 8 in a feature indication window 7 and media playback begins from a corresponding position in the media file.
  • FIG. 13 is a schematic block diagram of a preferred embodiment of a media browser 100 in accordance with the invention.
  • the media browser 100 preferably includes a general purpose computer 110 that has a controller 111 .
  • the controller 111 can be implemented as a single special purpose integrated circuit (e.g., ASIC) each having a main or central processor section for overall, system-level control, and separate sections dedicated to performing various different specific computations, functions and other processes under the control of the central processor section.
  • the controller 111 can also be implemented as a single microprocessor circuit or a plurality of separate dedicated or programmable integrated or other electronic circuits or devices, e.g., hardwired electronic or logic circuits such as discrete element circuits or programmable logic devices.
  • the controller 111 and/or the general purpose computer 110 also preferably include other circuitry or components, such as memory devices, relays, mechanical linkages, communications devices, etc., to effect desired control and/or input/output functions.
  • the general purpose computer 110 also includes a feature selector 112 , a position indicator 113 , a feature indicator 114 and a mapping module 115 , which are all preferably implemented as software modules that include sets of instructions performed by the general purpose computer 110 and/or the controller 111 .
  • these elements like the controller 111 , can be implemented as an ASIC or an array of ASICs, separate dedicated or programmable integrated or other electronic circuits or other devices.
  • a media input device 120 preferably inputs a media file in the form of a data stream to the general purpose computer 110 .
  • the media input device 120 can include one or more of any of the following devices: a semiconductor memory device, CD-ROM device, magnetic disk drive, other volatile or non-volatile memory devices, communications devices, such as a modem, facsimile transmitter or receiver, local-area or wide-area network devices, telecommunications devices, or other wired or wireless communications devices.
  • the media input device 120 can be any device that transmits a data stream representing a media file to the general purpose computer 110 .
  • the data stream transmitted from the media input device 120 to the general purpose computer 110 can take any of many different forms.
  • the data stream can be analog or digital data that is either compressed or uncompressed, and the data can be provided in parallel or serial form at any desired transmission rate using any desired transmission protocol, if any.
  • the controller 111 preferably communicates with a display 130 , such as a CRT or LCD display.
  • a display 130 is not limited to these types of displays.
  • the display 130 can include any device capable of presenting a representation of a media file to a user, including an audio speaker, visual display device, touch display (such as a Braille device), etc.
  • the media browser 100 also preferably includes a user interface 140 , such as a keyboard and/or computer mouse, that permits a user to communicate with the controller 111 .
  • a user interface 140 such as a keyboard and/or computer mouse
  • Other devices can be used with the user interface 140 , including touch screen devices, light pens, voice activated and/or voice recognition systems, etc.
  • the user interface 140 may include a general purpose computer and appropriate communications devices to send and receive signals to a more remotely located general purpose computer 110 , i.e., a remote server.
  • the general purpose computer 110 can send display control signals to the user interface 140 , which directly controls the display 130 .
  • the user interface 140 can perform some or all of the functions performed by the general purpose computer 110 , and some or all of the modules, such as the position indicator 113 , mapping module 115 , etc., can operate, at least in part, within the user interface 140 .
  • the media input 120 can be physically located near the general purpose computer 110 , the user interface 140 (e.g., a CD-ROM drive), or at some other location. Alternately, the media input 120 can be formed of a multitude of media sources, such as magnetic hard drives distributed over a wide network. All that is required is that the media stored in the media input 120 be accessable to the media browser 100 .
  • the media browser 100 receives a command from a user via the user interface 140 indicating a desire to browse a media file.
  • the desired media file is then either transmitted from the media input device 120 to the general purpose computer 110 or the media file is retrieved from a memory device provided as part of the controller 111 , for example.
  • the controller 111 preferably sends a signal to the display 130 to display the graphical user interface 10 to the user.
  • a command to indicate a current position of the media file is the beginning of the media file. That is, the thumb 31 on the timeline 3 is displayed at the far left position. Of course, the thumb 31 need not be displayed, or can be displayed at any desired position along the timeline 3 .
  • a video frame if present, is displayed in the video display portion 1 corresponding to a current position in the media file.
  • the signal provided by the controller 111 to the display 130 regarding the position of the thumb 31 is based on a signal provided by the position indicator 113 , which keeps track of a current position in the media file.
  • the user After viewing the graphical user interface 10 , the user preferably selects at least one feature of the media file using the media feature selection 4 and the user interface 140 .
  • Feature selection indications are provided to the feature selector 112 , which stores the selected features and provides a signal to the controller 111 to display the selected features in a selected feature window 5 of the interface 10 .
  • the feature selector 112 also provides an indication to the controller 111 if a selected feature is not selectable. For example, if a user selects a feature that is not present in a media file, e.g., a user selects the shot detect feature for a media file that does not contain video information, an indication that the selected feature is not selectable is provided to the user.
  • the feature selector 112 provides a list of selectable features to the controller 111 so that only selectable features are displayed in the media feature selection 4 .
  • the mapping module 115 generates and/or retrieves confidence scores corresponding to the selected features.
  • metadata values for all of the selectable features are precomputed and stored with the media file so that metadata values need not be generated during a browsing session.
  • the mapping module 115 can automatically generate metadata values and map the metadata values to corresponding confidence score values “on the fly.”
  • the feature indicator 114 generates and provides information to the controller 111 to display feature indications related to the selected features.
  • a user can select a portion of the media file for review, or perform other actions, such as zooming the timeline 3 , moving the timeline thumb 31 , etc.
  • a user can input signals to the media browser 100 to playback or otherwise manipulate the media file. For example, the user can click on an icon 8 in a feature indication window 7 and the controller 111 controls the display 130 to provide a representation of the media file starting from a time-wise position in the media file consistent with the selected icon 8 .
  • FIG. 14 is a flowchart that describes in further detail how a user chooses a media file for browsing and provides a corresponding signal to the media browser 100 .
  • the controller 111 sends a signal to the display 130 to display a media selection screen.
  • the displayed selection screen includes at least the display shown in FIG. 15.
  • the selection screen preferably includes several rows 200 , each row 200 displaying information for a corresponding media file.
  • Each row 200 preferably includes such information as a keyframe 201 , a timeline 202 , a media file name 203 , identifying information, such as a date, 204 , and a keyword listing 205 .
  • the keyframe 201 is preferably selected from a particularly relevant portion of the media file or otherwise visually conveys information related to the overall content of the media file.
  • the timeline 202 is similar to the timeline 3 in the graphical user interface 10 .
  • the timeline 202 preferably displays information related to a selected media feature, e.g., shot boundaries.
  • a user can view keyframes or other video information when a cursor 206 is moved over the timeline 202 .
  • keyframes are represented on the timeline 202 by a small icon that preferably changes appearance when the icon is nearest the cursor 206 .
  • Keyframes can be automatically selected based on confidence score information or can be previously identified by an operator.
  • the media browser 100 could display a predefined summary video sequence or another shortened representation that provides a user additional information to make a selection decision.
  • the timeline 202 can also provide other information related to media features in any of the ways described above. For example, icons, color sequences or keyframes could be displayed on the timeline 202 to provide media feature information.
  • the media feature information can be displayed based on metadata and confidence score information or based on predefined summary information provided by a user.
  • a user can search a database of media files by the name 203 , identifying information 204 and/or keywords 205 to narrow an initial search and generate an initial display of media file rows 200 on the selection screen.
  • the user can search using any known search screen, such as those associated with electronic database applications or Internet browser/search engines.
  • the media browser 100 can be very useful in browsing media files posted on a large network, such as the Internet, since the media browser 100 allows a user to rapidly and accurately identify and experience desired portions in media file.
  • the media displayed on the initial selection screen are preferably sorted, placing those media files most relevant to the search at the top. Sorting can be done based on confidence score information, search results (e.g., number of hits in a media file), or other desired criteria.
  • step S 120 the user reviews the media files, either by viewing keyframes, keywords, selected portions of the media files using the timeline 202 features, or by reviewing the media files in any of the ways discussed above.
  • step S 130 the user selects one or more of the media files for browsing. Preferably, the user selects a media file by clicking on an associated keyframe 201 , but the user can select media files in other ways, such as by entering a media file name or other identifier by keyboard.
  • FIG. 16 is a flowchart that describes in further detail how the mapping module 115 generates and/or retrieves confidence scores.
  • step S 510 the mapping module 115 generates and/or retrieves metadata information for the selected features.
  • the metadata information is preferably precomputed and stored along with the media file.
  • the mapping module 115 can apply any of the above described automatic techniques to the media file to generate metadata information.
  • the mapping module 115 can receive manually input metadata information from a user.
  • the mapping module 115 optionally processes the metadata information as desired in preparation for mapping the metadata to confidence scores. For example, the mapping module 115 thresholds, combines, filters or otherwise processes the metadata information in preparation for mapping the metadata information to confidence scores.
  • step S 530 the mapping module maps the processed metadata information to confidence score values for each selected feature using a desired function, e.g., a one-to-one mapping, other linear or non-linear functions, etc.
  • a desired function e.g., a one-to-one mapping, other linear or non-linear functions, etc.
  • FIG. 17 is a flowchart describing in further detail how the feature indicator 114 provides feature information for the selected features.
  • the feature indicator 114 processes the confidence scores for each selected feature as desired. For example, the feature indicator 114 thresholds, filters, combines, etc., the confidence score values as discussed above in preparation for providing feature information.
  • step S 620 the feature indicator 114 generates information to display feature indications for each of the selected features based on the processed confidence scores. For example, the feature indicator 114 generates signals to display feature indications in a feature indication window 6 .
  • FIG. 18 is a flowchart describing in further detail how the controller 111 controls media playback as desired.
  • a user optionally selects features using the key playback buttons 9 on the graphical user interface 10 .
  • the user could select the “speaker MD” feature.
  • the controller 111 inputs a playback control signal received from a user and adjusts the media playback based on the features selected in step S 710 .
  • the user could select the play button, and the media browser 100 adjusts the replay of the media file based on the “speaker MD” feature.
  • the media browser 100 could adjust the playback speed according to Equation 2:
  • R is the playback rate
  • C is the confidence score for the speaker MD feature
  • M is a maximum playback rate, which is preferably set by a user.
  • the confidence score C varies between 0 and 1. Therefore, as the confidence score increases (indicating that the speaker MD is speaking or is depicted in the media file), the playback rate approaches the value C. In contrast, as the confidence score decreases (indicating that the speaker MD is not featured in the media file), the playback rate approaches the maximum playback rate M, thereby speeding replay in sections where the speaker MD is not present in the media file.
  • the media browser 100 can control the media playback controls based on a selected feature.
  • the media browser 100 can also control the stop button to stop playback at a point in the media file where a feature is no longer present (e.g., a speaker leaves the room) or where a feature next occurs (e.g., stop at the next shot boundary).
  • the index controls can be controlled to jump to a point in the media file where a feature is present in or absent from the media file.
  • the timeline thumb 31 can be controlled based on a selected feature.
  • the thumb 31 could change its appearance, e.g., color, when the thumb 31 is moved over a media file portion where a selected feature is present, or the thumb 31 could be “indexed” so that a user can only move the thumb 31 within portions of the media file where a selected feature is present or absent.
  • control of the playback controls, including the thumb 31 is based on the confidence score value for a selected feature. Determination of whether a feature is present or not in a media file is preferably based on the confidence score value, e.g., if the confidence score exceeds/is below a desired threshold the media browser 100 determines that the feature is present in/absent from the media file.
  • FIG. 19 is a flowchart describing in further detail another way how the controller 111 optionally controls media playback.
  • a user selects a confidence score indication in a feature indication window 6 .
  • a user can select (e.g., double click) an icon 8 displayed in a feature indication window 6 .
  • the controller 111 accesses the media file and controls the display 130 to begin playback at a point in the media file corresponding to the selected confidence score indication. Playback can be of selected portions of the media file of particular interest determined based on confidence score values.

Abstract

A media browser, graphical user interface and method for browsing a media file wherein a user selects at least one feature in a media file and is provided with information regarding the existence of the selected feature in the media file. Based on the information, the user can identify and playback portions of interest in a media file.
Features in a media file, such as a speaker's identity, applause, silence, motion, or video cuts, are preferably automatically time-wise evaluated in the media file using known methods. Metadata generated based on the time-wise feature evaluation are preferably mapped to confidence score values that represent a probability of a corresponding feature's existence in the media file. Confidence score information is preferably presented graphically to a user as part of a graphical user interface, and is used to interactively browse the media file.

Description

    BACKGROUND OF THE INVENTION
  • 1. Field of Invention [0001]
  • This invention relates to a method and apparatus for reviewing an aural and/or visual and/or other representation of a media file. Specifically, the invention relates to using media content features to allow a user to more easily review a media file. [0002]
  • 2. Description of Related Art [0003]
  • Text documents often have many cues, such as headings, paragraphs, punctuation, etc., that allow a reader to quickly determine the beginning and end of different sections of the document and to aid the reader in finding areas of interest. However, video and audio browsing systems typically do not provide information to the user regarding simple features, like section beginning and end points, much less more complicated information, like the name of the speaker on a video clip. Such browsing systems typically offer only standard “VCR-type” playback control options, like play, stop, rewind, and fast forward. As anyone who has tried to find a specific video clip on a conventional video tape using a standard VCR will understand, it is often difficult to locate portions of interest in a video using the standard playback controls. [0004]
  • Many techniques exist for extracting information that represents the feature content of a media file. In this application, the term media or media file is used to represent any data stream that contains information regarding video or other image information, audio information, text information and/or other information. A feature of a media file is a property of the video, audio and/or text information in the media file, such as video or audio format, or information relating to the content of the media file, such as the identity of a speaker depicted in a video sequence, occurrences of applause, video shot boundaries, or motion depicted in a video sequence. For example, Pfeiffer et al., “Automatic Audio Content Analysis” ACM MULTIMEDIA 96, Boston, Mass., 1996, pp. 21-30; Wilcox, et al., “Segmentation of Speech Using Speaker Identification”, Proc. ICASSP 94, vol. S1, April 1994, pp. 161-164; and Foote, “Rapid Speaker ID Using Discrete MMI Feature Quantisation,” Expert Systems with Applications, vol. 13, no. 4, 1997, pp. 293-289, describe various methods for identifying audio features, such as music, human speech, and speaker identity. Regarding video data, Boreczky et al., “Comparison of Video Shot Boundary Detection Techniques” Proc. SPIE Conf. On Storage and Retrieval for Still Image and Video Databases IV, San Jose, Calif, vol. 2670, February 1996, pages 170-179, and Zhang et al., “Automatic Partitioning of Full-motion Video”, Multimedia Systems, vol. 1, no. 1, 1993, pp. 10-28, disclose methods for identifying shot boundaries (radical changes in video content) and motion. As described in these and other similar references, features in a media file can be identified automatically using any of a number of different techniques. [0005]
  • SUMMARY OF THE INVENTION
  • Providing feature information in a media browsing system can be very useful for a user when identifying areas of interest in a media file, controlling media playback, editing a media file, or performing other operations with a media file. For example, graphically identifying areas in a media file where a particular speaker is shown on a video clip can allow a user to quickly determine and playback those portions that contain the speaker. [0006]
  • Providing feature information to the user based on automatically identified features also eliminates the need for a user to manually index or otherwise mark significant portions of the media file for later retrieval. Thus, the invention can use existing methods for automatically identifying features in a media file to generate and provide feature information to a user to aid the user in browsing the media file. [0007]
  • The invention provides a media browser that uses media feature information as an aid in navigating, selecting, editing, and/or annotating a media file. [0008]
  • In one aspect of the invention, media features are selected by a user. [0009]
  • In one aspect of the invention, media browsing functions, such as play, rewind, stop, fast-forward, index, automatic slide show, and automatic preview, are controlled based on feature information. [0010]
  • In one aspect of the invention, feature information for a selected feature is mapped to a corresponding confidence score. [0011]
  • In one aspect of the invention, the media browser includes a feature indicator that provides information related to a corresponding selected feature based on a corresponding confidence score. [0012]
  • In one aspect of the invention, a feature indicator combines at least two confidence scores and provides information based on the combination. [0013]
  • In one aspect of the invention, a feature indicator provides information related to a confidence score based on a value of another confidence score. [0014]
  • The invention also provides a method for browsing a media file. A feature of the media file being browsed is selected and information related to a confidence score for at least one selected feature is provided. The confidence score relates to the existence of a corresponding selected feature in the media file. Based on the information related to the confidence score, a portion of the media file is selected. [0015]
  • In one aspect of the invention, a metadata value representing a time-wise evaluation of a feature in the media file is mapped to a corresponding confidence score. [0016]
  • In one aspect of the invention, mapping of a metadata value to a corresponding confidence score is non-linear. [0017]
  • In one aspect of the invention, mapping of a metadata value to a confidence score is dependent on a user-defined control value or values.[0018]
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • The invention will be described in relation to the following drawings in which reference numerals refer to like elements, and wherein: [0019]
  • FIG. 1 is an example screen display for a graphical user interface in accordance with the invention; [0020]
  • FIG. 2 shows example metadata values, corresponding confidence score information, and an example graphical depiction of corresponding feature information; [0021]
  • FIGS. [0022] 3-9 show different ways of graphically depicting information related to a feature in a media file;
  • FIG. 10 is an example screen display depicting how features can be combined and corresponding combined feature information can be shown; [0023]
  • FIG. 11 is an example screen display depicting how display of feature information relating to a corresponding feature can be conditioned on another feature; [0024]
  • FIG. 12 is a flow chart explaining basic steps of a preferred method for browsing a media file; [0025]
  • FIG. 13 is a schematic block diagram of a preferred media browser in accordance with invention; [0026]
  • FIG. 14 is a flow chart of steps of a preferred method for selecting a media file to be browsed; [0027]
  • FIG. 15 is a preferred media selection screen; [0028]
  • FIG. 16 is a flow chart of steps of a preferred method for mapping feature metadata to a corresponding confidence score; [0029]
  • FIG. 17 is a flow chart of steps of a preferred method for processing confidence scores and providing information related to the confidence scores; [0030]
  • FIG. 18 is a flow chart of steps of a preferred method for controlling playback functions based on a selected feature; and [0031]
  • FIG. 19 is a flow chart of steps of a preferred method for reviewing a media file based on selection of a confidence score indication.[0032]
  • DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
  • The invention is described in connection with browsing a media file. As used herein, browsing refers to any operation related to reviewing, manipulating, editing, selecting portions of, storing, transmitting, or other operations related to a media file. In addition, a preferred embodiment of a graphical user interface for a media browser is described below having specific functions. In many cases, various functions of the media browser can be eliminated or altered, as desired. For example, information that is displayed graphically in the embodiment described below can be provided aurally or otherwise, as described more fully below. [0033]
  • As discussed above, several methods exist for automatically deriving information that represents the likelihood of the existence of a feature in a media data stream. Such information, called metadata, can be very useful and provides cues for locating portions of interest in a media file. For example, automatic methods exist for identifying silent portions in audio data. Identifying such portions can be useful in editing the audio data because, if silent portions are identified, an edit region of the audio data can be bounded by the silent portions, thereby insuring that speech in the edit region is not cut mid-word or mid-sentence. [0034]
  • As another example, a common video analysis technique is the detection of shot boundaries, which represent significant differences between consecutive video frames. As is well known, the difference between consecutive video frames can be determined based on statistical properties of the pixels in the frame images, histogram differences, compression algorithms, edge differences, or motion detection. Application of one of several known techniques for detecting shot boundaries results in a series of time-varying metadata values that each represent a difference between consecutive video frames. Once metadata regarding the shot boundary feature is determined, information can be provided to a user to aid the user in locating portions of interest in the media file, e.g., places in the media file where scene changes occur. [0035]
  • Although metadata can be automatically generated, metadata can be input by a user or group of users. For example, a user could review a media file and identify sections of the media file where a particular speaker is featured, e.g., the speaker is either shown visually or is speaking. After identifying portions of the media file where a speaker is featured, the user can manually enter metadata that indicates the user's subjective evaluation of whether the speaker is present in the media file at each time-wise position in the media file. The user can enter the metadata continuously after viewing each video frame or listening to each predefined sub-portion of the media file. Alternately, the user could identify onoy those portions of the media file where the speaker is featured, and all other portions of the media file could be assigned metadata values that indicate that the speaker is not present in the media file. [0036]
  • FIG. 1 shows an example [0037] graphical user interface 10 in accordance with the invention. The graphical user interface 10 is typically displayed on a video display, such as a computer monitor, but can be presented to a user on any other display device. The interface 10 has a video display portion 1 in which a still video frame representation of an image contained in a media file can be presented. Video frames can also be displayed at any desired video frame rate, such as that performed on a standard computer monitor or television set. Audio representations of sound information contained in a media file can be presented to a user by a speaker (not shown). Alternately, visual representations of sound information, such as a waveform, can be presented on the graphical user interface 10.
  • A [0038] playback control bar 2 contains playback controls that are used to control how a visual and/or aural representation of a media file is presented to a user. For example, the playback control bar 2 can include buttons for controls such as play, stop, rewind, fast forward, and forward and reverse index. The playback controls shown in FIG. 1 are not intended to be an exhaustive representation of all of the different types of playback controls that can be provided. For example, controls can be provided to alter the effective frame rate at which a video display is generated or the speed at which a sound representation is played back. As with other features of the interface 10, a user activates controls on the playback control bar 2 by clicking a desired button with a mouse cursor. Other methods for activating the controls can be used, such as individual keystrokes or combinations of keystrokes on a keyboard, selection of controls using a touch screen or light pen, or other selection device.
  • A [0039] timeline 3 includes a thumb 31 that indicates a current time-wise position in the media file. The timeline 3 shown in FIG. 1 ranges from time 0:00 to time 47:38 and can be optionally zoomed in or out and panned using the timeline controls 32. The thumb 31 can be moved time-wise along the timeline 3 by using the left and right timeline controls 32. Alternately, a user could select the thumb 31 using a mouse and move the thumb 31 to a desired position along the timeline 3 using the mouse. By moving the thumb 31 time-wise along the timeline 3, a corresponding video and/or aural representation of the media file located at the time-wise position of the thumb 31 can be played back. For example, video frames or preselected keyframes at corresponding time-wise locations in the media file can be displayed in the video display portion 1 as the thumb 31 is moved. Alternately, video/aural playback could begin from a corresponding position in the media file after the thumb 31 is moved to a desired position and released.
  • A user can select a feature in the media file using a [0040] media feature selection 4. The feature selection 4 includes a scroll bar for navigating through a list of selectable features. Preferably, features in the feature selection 4 are selected by double clicking a desired feature with a mouse cursor. Alternately, a user could type in a selected feature using a keyboard or otherwise enter a selected feature, such as by speaking a selected feature, which is recognized by the browsing system using voice recognition techniques. Preferably, the features listed in the feature selection 4 are organized in alphabetical order or otherwise grouped logically. For example, video-related features are preferably grouped apart from audio-related features.
  • Selected features are displayed in selected [0041] feature windows 5. In the example graphical user interface 10 of FIG. 1, three selected feature windows 5-1, 5-2, and 5-3 are shown. However, fewer or more selected feature windows 5 could be used. Corresponding to each selected feature window 5 is a feature indication window 6. The feature indication window 6 preferably graphically indicates the time-wise presence or absence of a corresponding feature in the media file, but the feature indication window 6 could display other information related to the corresponding feature. For example, the feature indication window 6-3 graphically displays the time-wise presence of applause in the media file. In this example, solid vertical lines displayed in a feature indication window 6 indicate a determination that the corresponding feature is likely present in the media file at the corresponding time-wise location in the media file. However, other representations are possible, as discussed more fully below.
  • A feature summary bar [0042] 7 preferably graphically displays a summary of the selected features. In this example, the feature summary bar 7 includes graphical icons 8 that each indicate, or represent, specific information. For example, the scissors icon 8 indicates the presence of a cut or shot detect in the media file. The icons 8 can also indicate information related to two or more features. For example, a rectangular icon 8 containing a circle indicates a portion of the media file that contains an occurrence of applause followed shortly after a shot detect occurrence. This is only one example of the possible icons 8 that can be used to summarize selected features. Additional summary representations are discussed below.
  • [0043] Key playback buttons 9 are also provided for each of the selected features and for the feature summary bar 7. The key playback buttons 9 allow a user to select a feature that is used to control playback functions of the playback control bar 2. For example, if the key playback button 9 for the selected feature “speaker MD” is selected, the play and/or index buttons in the playback control bar 2 could be controlled such that whenever the button is selected, portions of the media file containing the speaker MD are “jumped” to and played back. Other portions of the media file are skipped and not presented to the user. As another example, if the key playback button 9 for the selected feature “applause” is selected, the index buttons in the playback control bar 2 could be controlled such that whenever an index button is selected, a representation of the media file begins immediately before or after occurrences of applause in the media file.
  • The [0044] interface 10 also includes a confidence score value manipulation control 11 that allows a user to adjust confidence score values for corresponding features as desired. As explained more fully below, a confidence score relates to a corresponding feature, is preferably determined using metadata for a corresponding feature, and preferably is used to generate the information displayed in the feature indication windows 6.
  • Because automatic techniques for generating metadata for media features do not always work reliably, the metadata itself is not always easy to interpret, and the metadata rarely positively indicate the absolute presence or absence of a feature in a media file, automatically derived metadata is preferably mapped to a corresponding confidence score. The confidence score is thus intended to convey to a user, in an understandable form, the probability of a feature's existence in the media file. Preferably, the metadata is mapped to a corresponding time-varying confidence score using some function that is based on prior knowledge about the metadata's reliability. However, mapping of the metadata to a confidence score can be performed in a one-to-one relationship, where individual metadata data values are equal to corresponding confidence score values. [0045]
  • FIG. 2 shows an example of shot detect metadata derived from a media file containing video information. The metadata values are represented graphically, and in this example, relatively larger metadata values represent relatively large differences between consecutive video frames at a corresponding time-wise position in the media file. [0046]
  • In the example shown in FIG. 2, metadata representing shot boundary values are mapped to a confidence score using a threshold. If a metadata value is above the threshold, the corresponding confidence score is assigned a value of one, indicating a relatively high probability that a video cut is present in the media file. If the metadata value is below the threshold, the corresponding confidence score is assigned a value of zero. Preferably, the threshold is adjusted automatically or by a user based on the reliability of the metadata. The confidence scores for the shot detection feature can be depicted in a [0047] feature indication window 6 of a graphical user interface 10 as shown in FIG. 2. In this example, dark portions of the feature indication window 6 represent a confidence score of zero and light portions of the feature indication window 6 represent confidence score values of one.
  • As will be understood by those of ordinary skill in the art, the metadata values for a media feature can be mapped to a confidence score in many different ways. As discussed above, the metadata values are preferably mapped to corresponding confidence score values using a function that is determined based on the feature corresponding to the metadata and the reliability of metadata. Linear or non-linear mapping, including normalization, thresholding and filtering, can be performed for numerical metadata. For non-numerical metadata, such as text, closed captions (subtitles), or MIDI streams, metadata can be mapped to confidence score values using statistical or other mathematical methods. For example, the time-wise frequency of a word or set of words in a media data stream could be converted to a set of confidence score values where a relatively high confidence score value is assigned to a portion of the media file that contains relatively more occurrences of the word or set of words, and lower confidence scores are assigned to portions containing fewer occurrences of the word or set of words. [0048]
  • For multi-dimensional data, such as metadata generated by a face recognition algorithm, a lower dimensional confidence score can be computed. In a preferred embodiment, a face recognition algorithm generates five numerical values for each face detected in a video frame: the coordinates of the upper left and lower right corners of the bounding rectangle of the candidate face, and how well the candidate matches the face template. A confidence score for the face is preferably determined according to Equation 1:[0049]
  • C=MS(CA/MFA)  (1)
  • where C is the confidence score, MS is the value representing how well the candidate matches the face template, CA is the area of the candidate face determined from the upper left and lower right comer coordinates, and MFA is the maximum face area (a constant). In this example, CA is preferably not larger than or constrained to be not larger than MFA. [0050]
  • Mapping metadata values to confidence score values can be performed according to functions that are “learned” using techniques such as learning Bayesian networks. For example, a confidence score mapping system could “learn” that metadata determined for a particular feature is more or less reliable than originally anticipated, and adjust the mapping function, e.g., a mapping threshold, accordingly. [0051]
  • Mapping of metadata values is also preferably controlled based on user control values. For example, a user can adjust a threshold value or other control values using the confidence score [0052] value manipulation control 11 in the graphical user interface 10. Using the example in FIG. 2, adjusting the sliders on the confidence score value manipulation control 11 can adjust the threshold value or values used to map the metadata to confidence scores. By adjusting the threshold value(s), the user can adjust the sensitivity of the mapping function to the metadata and customize the feature information displayed in the feature indicator windows 6. In the FIG. 2 example, only one threshold is used and so only one slider need be displayed on the confidence score value manipulation control 11. However, more than one threshold can be used to map metadata to confidence scores and so an additional slider can be displayed. Further, other graphical controls, such as dials, up/down buttons, numerical indicators, etc., in addition to or in place of the sliders can be used. The confidence score value manipulation control 11 can also be used to adjust mapping control values other than thresholds, such as filter coefficient values, or any other value used to change the way metadata is mapped to confidence score values.
  • After confidence score values are determined for a feature, the confidence score information is preferably provided to a user as an aid in browsing a media file as discussed above. FIGS. [0053] 3-9 show additional examples of how confidence score information can be presented to a user. These examples are not intended to be exhaustive and other methods can be used to provide confidence score information. For example, confidence score information can be conveyed to stimulate human senses other than sight, including sound, touch (e.g., by activating a Braille touchpad) or smell.
  • The examples shown in FIGS. [0054] 3-6 involve a selected feature “speaker MD”. This feature represents a speaker depicted and/or recorded in a media file where MD represents the speaker's initials. In this example, metadata related to the speaker's identity can be generated using face recognition techniques, in the case where the speaker is identified “visually” or using speech recognition techniques, where the speaker is identified as having a particular speech pattern, for example. The speaker's identity can also be verified manually by a user. For example, a user can review a media file and enter metadata directly into the system indicating whether a particular speaker is featured in the media file. The user can also enter metadata for other feature types, thereby eliminating a need to have the metadata determined automatically.
  • FIG. 3 shows an example [0055] feature indication window 6 containing icons 8. The icons 8 represent likely portions in a media file where the speaker MD either talks or is represented visually. In this example, portions where the speaker MD either talks or is represented visually are identified as those portions for which the confidence score exceeds a given threshold. The icons 8 optionally contain a representation of speaker MD's face or is a thumbnail keyframe extracted from the media file at a corresponding point in the media file. Preferably, when a user clicks on an icon 8, a representation of the media file at a point corresponding in time is presented to the user.
  • In FIG. 4, portions of the media file that most likely contain the speaker MD are indicated by shaded portions in the [0056] feature indication window 6. Optionally, the shaded portions can include color. For example, speaker MD could be assigned the color green, and all green portions displayed in the feature indication window 6 indicate portions of the media file most likely containing the speaker MD. In this example, as in all cases, the display is generated based on the corresponding confidence score, which may not always accurately indicate if the corresponding feature is present in the media file. Instead, as discussed above, the metadata and corresponding confidence score represents a probability or “best guess” regarding whether the feature is present in the media file. This may be true even when a user enters the metadata into the system. For example, a user may not be certain that a particular person is speaking in a media file even though the user is very familiar with the person's voice.
  • In FIG. 5, the confidence score corresponding to speaker MD, or a normalized version of the confidence score, is displayed in the [0057] feature indication window 6. In this type of display, the metadata corresponding to speaker MD can be directly mapped on a one-to-one basis to the confidence score. That is, the metadata values are the same as the corresponding confidence score values. As can be seen in FIG. 5, the confidence score values may not always indicate that the speaker MD is either positively included or not included in the media file. Rather, the confidence score values can vary indicating an uncertainty regarding whether the corresponding feature is present in the media file. This uncertainty may be due to noise in the media data stream, two or more speakers speaking simultaneously, or that a portion of the speaker's face is partially obscured.
  • In FIG. 6, the confidence score values shown in FIG. 5 have been thresholded to generate the display in the [0058] feature indication window 6. In this example, any confidence score values that fall below the maximum value are clipped to the lowest possible value. As discussed above, a user can vary the threshold values used to process the confidence score values to generate the feature indication using the confidence score value manipulation control 11, or otherwise vary how the feature indication is presented based on the confidence score values.
  • FIGS. [0059] 7-9 relate to the display of confidence score information for a video cut feature in a media segment. In FIG. 7, the confidence score values are shown without manipulation in the feature indication window 6. In this case, increasing confidence score values indicate higher probabilities that a video cut has been detected. In FIG. 8, the video cut feature indication shown in the feature indication window 6 is generated based on integrating the confidence score values over time. This type of indication can be useful for determining the total number of video cuts in a media segment or in determining how much the video images change within the media segment. Thus, the change in the integrated value is proportional to the fraction of total accumulated feature change in the media file. Optionally, the curve indicating the integrated value of the confidence score values shown in FIG. 8 can vary in color as the curve represents an increase in value. For example, the curve could start as a blue color for relatively low values and gradually change to a red color for maximum integration values. That is, the curve could start as a blue color and as the curve increases in value, the curve gradually changes through various shades of purple of increasing red content. FIG. 9 shows an alternate representation of the integrated confidence score value where the integrated value is represented only by a corresponding color change in the feature indication window 6 without display of the integration curve itself. In this example, the change in color represents the total accumulated feature change in the media file.
  • The [0060] graphical user interface 10 preferably includes an option for combining features and displaying confidence score information based on the feature combination, as shown in FIG. 10. In this example, the features “speaker MD” and “applause” are combined, and the corresponding feature indication window 6 indicates media portions where the speaker MD is depicted during applause. This type of combination can be useful to locate portions in a media file where a particular speaker begins and/or ends a presentation or has made a particularly interesting comment during a presentation.
  • FIG. 10 shows another combination of the features “silence” and “shot detect”. The corresponding [0061] feature indication window 6 indicates portions in the media file where a shot detect and silence are simultaneously present. This combination can be useful to indicate the beginning or end of a desired portion in the media file.
  • As will be appreciated, other feature combinations are possible. For example, a combination of speech detection and motion detection could provide useful information regarding gestures made by a speaker. In addition, more than two features can be combined to generate more sophisticated feature indication information. Preferably, the [0062] graphical user interface 10 includes a “Combine” button that a user can click to combine two or more features. However, a user can define which features to combine by other methods.
  • As shown in FIG. 11, display of confidence score information can be conditioned on other features. In this example, confidence score information related to the feature “speaker MD” is displayed only when confidence score information indicates a relatively high probability that the speaker MD is shown in a video segment of the media file along with or within two minutes of applause in the soundtrack of the media file. As will be appreciated by those of ordinary skill in the art, other feature combinations or conditions, e.g., Boolean operators, can be used depending on the type of feature indication information needed for a specific task and the relevant features. [0063]
  • FIG. 12 is a flowchart of a preferred method for browsing a media file. In step S[0064] 10, a user inputs a command indicating a desire to browse a media file. In step S20, the desired media file is retrieved. In step S30, the graphical user interface 10 is preferably displayed to the user, although other interfaces can be used. In step S40, the user preferably selects at least one feature of the media file. In step S50, confidence scores corresponding to the selected features are retrieved and/or generated. Preferably, metadata values for all of the selectable features are precomputed and stored with the media file so that metadata values need not be generated during a browsing session. However, the metadata values and corresponding confidence score values can be generated during a browsing session.
  • In step S[0065] 60, feature indications related to the selected features are displayed to the user. In step S70, the user enters commands to play back or otherwise manipulate the media file as desired. For example, a user can click on an icon 8 in a feature indication window 7 and media playback begins from a corresponding position in the media file.
  • FIG. 13 is a schematic block diagram of a preferred embodiment of a [0066] media browser 100 in accordance with the invention. The media browser 100 preferably includes a general purpose computer 110 that has a controller 111. The controller 111 can be implemented as a single special purpose integrated circuit (e.g., ASIC) each having a main or central processor section for overall, system-level control, and separate sections dedicated to performing various different specific computations, functions and other processes under the control of the central processor section. The controller 111 can also be implemented as a single microprocessor circuit or a plurality of separate dedicated or programmable integrated or other electronic circuits or devices, e.g., hardwired electronic or logic circuits such as discrete element circuits or programmable logic devices. The controller 111 and/or the general purpose computer 110 also preferably include other circuitry or components, such as memory devices, relays, mechanical linkages, communications devices, etc., to effect desired control and/or input/output functions.
  • The [0067] general purpose computer 110 also includes a feature selector 112, a position indicator 113, a feature indicator 114 and a mapping module 115, which are all preferably implemented as software modules that include sets of instructions performed by the general purpose computer 110 and/or the controller 111. However, these elements, like the controller 111, can be implemented as an ASIC or an array of ASICs, separate dedicated or programmable integrated or other electronic circuits or other devices.
  • A [0068] media input device 120 preferably inputs a media file in the form of a data stream to the general purpose computer 110. The media input device 120 can include one or more of any of the following devices: a semiconductor memory device, CD-ROM device, magnetic disk drive, other volatile or non-volatile memory devices, communications devices, such as a modem, facsimile transmitter or receiver, local-area or wide-area network devices, telecommunications devices, or other wired or wireless communications devices. In short, the media input device 120 can be any device that transmits a data stream representing a media file to the general purpose computer 110.
  • The data stream transmitted from the [0069] media input device 120 to the general purpose computer 110 can take any of many different forms. For example, the data stream can be analog or digital data that is either compressed or uncompressed, and the data can be provided in parallel or serial form at any desired transmission rate using any desired transmission protocol, if any.
  • The [0070] controller 111 preferably communicates with a display 130, such as a CRT or LCD display. However, the display 130 is not limited to these types of displays. In short, the display 130 can include any device capable of presenting a representation of a media file to a user, including an audio speaker, visual display device, touch display (such as a Braille device), etc.
  • The [0071] media browser 100 also preferably includes a user interface 140, such as a keyboard and/or computer mouse, that permits a user to communicate with the controller 111. Other devices can be used with the user interface 140, including touch screen devices, light pens, voice activated and/or voice recognition systems, etc.
  • Where the invention is used over a more distributed system, such as the Internet, the [0072] user interface 140 may include a general purpose computer and appropriate communications devices to send and receive signals to a more remotely located general purpose computer 110, i.e., a remote server. In this case, the general purpose computer 110 can send display control signals to the user interface 140, which directly controls the display 130. In addition, the user interface 140 can perform some or all of the functions performed by the general purpose computer 110, and some or all of the modules, such as the position indicator 113, mapping module 115, etc., can operate, at least in part, within the user interface 140. The media input 120 can be physically located near the general purpose computer 110, the user interface 140 (e.g., a CD-ROM drive), or at some other location. Alternately, the media input 120 can be formed of a multitude of media sources, such as magnetic hard drives distributed over a wide network. All that is required is that the media stored in the media input 120 be accessable to the media browser 100.
  • In a preferred mode of operation, the [0073] media browser 100 receives a command from a user via the user interface 140 indicating a desire to browse a media file. The desired media file is then either transmitted from the media input device 120 to the general purpose computer 110 or the media file is retrieved from a memory device provided as part of the controller 111, for example. The controller 111 preferably sends a signal to the display 130 to display the graphical user interface 10 to the user. Preferably, included in the signal provided to the display 130 is a command to indicate a current position of the media file is the beginning of the media file. That is, the thumb 31 on the timeline 3 is displayed at the far left position. Of course, the thumb 31 need not be displayed, or can be displayed at any desired position along the timeline 3. Likewise, a video frame, if present, is displayed in the video display portion 1 corresponding to a current position in the media file. The signal provided by the controller 111 to the display 130 regarding the position of the thumb 31 is based on a signal provided by the position indicator 113, which keeps track of a current position in the media file.
  • After viewing the [0074] graphical user interface 10, the user preferably selects at least one feature of the media file using the media feature selection 4 and the user interface 140. Feature selection indications are provided to the feature selector 112, which stores the selected features and provides a signal to the controller 111 to display the selected features in a selected feature window 5 of the interface 10. The feature selector 112 also provides an indication to the controller 111 if a selected feature is not selectable. For example, if a user selects a feature that is not present in a media file, e.g., a user selects the shot detect feature for a media file that does not contain video information, an indication that the selected feature is not selectable is provided to the user. Preferably, the feature selector 112 provides a list of selectable features to the controller 111 so that only selectable features are displayed in the media feature selection 4.
  • Once media features are selected, the [0075] mapping module 115 generates and/or retrieves confidence scores corresponding to the selected features. Preferably, metadata values for all of the selectable features are precomputed and stored with the media file so that metadata values need not be generated during a browsing session. However, the mapping module 115 can automatically generate metadata values and map the metadata values to corresponding confidence score values “on the fly.”
  • Next, the [0076] feature indicator 114 generates and provides information to the controller 111 to display feature indications related to the selected features.
  • Based on the displayed feature indications, a user can select a portion of the media file for review, or perform other actions, such as zooming the [0077] timeline 3, moving the timeline thumb 31, etc. When the user makes a decision to review a portion of the media file, a user can input signals to the media browser 100 to playback or otherwise manipulate the media file. For example, the user can click on an icon 8 in a feature indication window 7 and the controller 111 controls the display 130 to provide a representation of the media file starting from a time-wise position in the media file consistent with the selected icon 8.
  • FIG. 14 is a flowchart that describes in further detail how a user chooses a media file for browsing and provides a corresponding signal to the [0078] media browser 100. In step S110, the controller 111 sends a signal to the display 130 to display a media selection screen. Preferably, the displayed selection screen includes at least the display shown in FIG. 15. The selection screen preferably includes several rows 200, each row 200 displaying information for a corresponding media file. Each row 200 preferably includes such information as a keyframe 201, a timeline 202, a media file name 203, identifying information, such as a date, 204, and a keyword listing 205. The keyframe 201 is preferably selected from a particularly relevant portion of the media file or otherwise visually conveys information related to the overall content of the media file. The timeline 202 is similar to the timeline 3 in the graphical user interface 10. The timeline 202 preferably displays information related to a selected media feature, e.g., shot boundaries. Preferably, a user can view keyframes or other video information when a cursor 206 is moved over the timeline 202. For example, when a user moves the cursor 206, a keyframe in the media file that is nearest in time to the cursor 206 position is displayed to the user. Keyframes are represented on the timeline 202 by a small icon that preferably changes appearance when the icon is nearest the cursor 206. Keyframes can be automatically selected based on confidence score information or can be previously identified by an operator. Alternately, the media browser 100 could display a predefined summary video sequence or another shortened representation that provides a user additional information to make a selection decision. The timeline 202 can also provide other information related to media features in any of the ways described above. For example, icons, color sequences or keyframes could be displayed on the timeline 202 to provide media feature information. The media feature information can be displayed based on metadata and confidence score information or based on predefined summary information provided by a user.
  • Preferably, a user can search a database of media files by the [0079] name 203, identifying information 204 and/or keywords 205 to narrow an initial search and generate an initial display of media file rows 200 on the selection screen. Preferably, the user can search using any known search screen, such as those associated with electronic database applications or Internet browser/search engines. In fact, the media browser 100 can be very useful in browsing media files posted on a large network, such as the Internet, since the media browser 100 allows a user to rapidly and accurately identify and experience desired portions in media file. To speed review and selection, the media displayed on the initial selection screen are preferably sorted, placing those media files most relevant to the search at the top. Sorting can be done based on confidence score information, search results (e.g., number of hits in a media file), or other desired criteria.
  • In step S[0080] 120, the user reviews the media files, either by viewing keyframes, keywords, selected portions of the media files using the timeline 202 features, or by reviewing the media files in any of the ways discussed above. In step S130, the user selects one or more of the media files for browsing. Preferably, the user selects a media file by clicking on an associated keyframe 201, but the user can select media files in other ways, such as by entering a media file name or other identifier by keyboard.
  • FIG. 16 is a flowchart that describes in further detail how the [0081] mapping module 115 generates and/or retrieves confidence scores. In step S510, the mapping module 115 generates and/or retrieves metadata information for the selected features. As described above, the metadata information is preferably precomputed and stored along with the media file. However, if metadata for a selected feature is not stored with the media file, the mapping module 115 can apply any of the above described automatic techniques to the media file to generate metadata information. In addition, the mapping module 115 can receive manually input metadata information from a user.
  • In step S[0082] 520, the mapping module 115 optionally processes the metadata information as desired in preparation for mapping the metadata to confidence scores. For example, the mapping module 115 thresholds, combines, filters or otherwise processes the metadata information in preparation for mapping the metadata information to confidence scores.
  • In step S[0083] 530, the mapping module maps the processed metadata information to confidence score values for each selected feature using a desired function, e.g., a one-to-one mapping, other linear or non-linear functions, etc.
  • FIG. 17 is a flowchart describing in further detail how the [0084] feature indicator 114 provides feature information for the selected features. In step S610, the feature indicator 114 processes the confidence scores for each selected feature as desired. For example, the feature indicator 114 thresholds, filters, combines, etc., the confidence score values as discussed above in preparation for providing feature information.
  • In step S[0085] 620, the feature indicator 114 generates information to display feature indications for each of the selected features based on the processed confidence scores. For example, the feature indicator 114 generates signals to display feature indications in a feature indication window 6.
  • FIG. 18 is a flowchart describing in further detail how the [0086] controller 111 controls media playback as desired. In step S710, a user optionally selects features using the key playback buttons 9 on the graphical user interface 10. For example, the user could select the “speaker MD” feature. In step S720, the controller 111 inputs a playback control signal received from a user and adjusts the media playback based on the features selected in step S710. For example, the user could select the play button, and the media browser 100 adjusts the replay of the media file based on the “speaker MD” feature. As one example, the media browser 100 could adjust the playback speed according to Equation 2:
  • R=C+M(1−C)  (2)
  • where R is the playback rate, C is the confidence score for the speaker MD feature, and M is a maximum playback rate, which is preferably set by a user. In this example, the confidence score C varies between 0 and 1. Therefore, as the confidence score increases (indicating that the speaker MD is speaking or is depicted in the media file), the playback rate approaches the value C. In contrast, as the confidence score decreases (indicating that the speaker MD is not featured in the media file), the playback rate approaches the maximum playback rate M, thereby speeding replay in sections where the speaker MD is not present in the media file. [0087]
  • This is only one example of how the [0088] media browser 100 can control the media playback controls based on a selected feature. The media browser 100 can also control the stop button to stop playback at a point in the media file where a feature is no longer present (e.g., a speaker leaves the room) or where a feature next occurs (e.g., stop at the next shot boundary). As discussed above, the index controls can be controlled to jump to a point in the media file where a feature is present in or absent from the media file. Further, the timeline thumb 31 can be controlled based on a selected feature. For example, the thumb 31 could change its appearance, e.g., color, when the thumb 31 is moved over a media file portion where a selected feature is present, or the thumb 31 could be “indexed” so that a user can only move the thumb 31 within portions of the media file where a selected feature is present or absent. Preferably, control of the playback controls, including the thumb 31, is based on the confidence score value for a selected feature. Determination of whether a feature is present or not in a media file is preferably based on the confidence score value, e.g., if the confidence score exceeds/is below a desired threshold the media browser 100 determines that the feature is present in/absent from the media file.
  • FIG. 19 is a flowchart describing in further detail another way how the [0089] controller 111 optionally controls media playback. In step S730, a user selects a confidence score indication in a feature indication window 6. For example, a user can select (e.g., double click) an icon 8 displayed in a feature indication window 6. In step S740, the controller 111 accesses the media file and controls the display 130 to begin playback at a point in the media file corresponding to the selected confidence score indication. Playback can be of selected portions of the media file of particular interest determined based on confidence score values.
  • While the invention has been described with reference to specific embodiments, the description of the specific embodiments is illustrative only and is not to be construed as limiting the scope of the invention. Various other modifications and changes may occur to those skilled in the art without departing from the spirit and scope of the invention as set forth herein. [0090]

Claims (3)

What is claimed is:
1. A media browser comprising:
a feature selection module that inputs at least one media feature selected by a user;
a media presentation device that provides an aural and/or visual representation of a media file being browsed; and
a feature indicator that provides information related to a confidence score for at least one selected media feature, the confidence score indicating a probability of existence of a corresponding selected media feature in the media file;
wherein the selected media feature is not used to perform, and is not related to, a text search of the media file.
2. A method of browsing a media file, comprising:
selecting a feature of a media file being browsed, the feature not being used to perform and not related to a text search of the media file;
providing information related to a confidence score for at least one selected feature relative to a segment of the media file, the confidence score indicating a probability of existence of a corresponding selected feature in the media file; and
selecting a portion of the media file based on the information related to a confidence score for at least one selected feature.
3. A graphical user interface for reviewing a portion of a stored data set, the stored data set including at least one of audio data and video data, the graphical user interface comprising:
a feature selection portion through which a user can select at least one data feature of the data set, the selected feature not related to, and not used to perform, a text search of the data set;
at least one data representation portion, each data representation portion representing the stored data set relative to one selected feature and containing at least one selectable feature indicator, each selectable feature indicator corresponding to a portion of the stored data set and providing information to the user related to a confidence score that indicates a probability of existence that the corresponding portion of the stored data set contains the corresponding selected feature.
US09/934,486 1998-09-11 2001-08-23 Media browser using multimodal analysis Abandoned US20020054083A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US09/934,486 US20020054083A1 (en) 1998-09-11 2001-08-23 Media browser using multimodal analysis

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US09/151,285 US6366296B1 (en) 1998-09-11 1998-09-11 Media browser using multimodal analysis
US09/934,486 US20020054083A1 (en) 1998-09-11 2001-08-23 Media browser using multimodal analysis

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US09/151,285 Continuation US6366296B1 (en) 1998-09-11 1998-09-11 Media browser using multimodal analysis

Publications (1)

Publication Number Publication Date
US20020054083A1 true US20020054083A1 (en) 2002-05-09

Family

ID=22538077

Family Applications (2)

Application Number Title Priority Date Filing Date
US09/151,285 Expired - Lifetime US6366296B1 (en) 1998-09-11 1998-09-11 Media browser using multimodal analysis
US09/934,486 Abandoned US20020054083A1 (en) 1998-09-11 2001-08-23 Media browser using multimodal analysis

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US09/151,285 Expired - Lifetime US6366296B1 (en) 1998-09-11 1998-09-11 Media browser using multimodal analysis

Country Status (2)

Country Link
US (2) US6366296B1 (en)
JP (1) JP2000090121A (en)

Cited By (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6711587B1 (en) 2000-09-05 2004-03-23 Hewlett-Packard Development Company, L.P. Keyframe selection to represent a video
US20040103372A1 (en) * 1997-12-22 2004-05-27 Ricoh Company, Ltd. Multimedia visualization and integration environment
US6782049B1 (en) * 1999-01-29 2004-08-24 Hewlett-Packard Development Company, L.P. System for selecting a keyframe to represent a video
USRE38609E1 (en) * 2000-02-28 2004-10-05 Webex Communications, Inc. On-demand presentation graphical user interface
EP1376584A3 (en) * 2002-06-19 2004-12-22 Microsoft Corporation System and method for automatically generating video cliplets from digital video
US20050151737A1 (en) * 2004-01-14 2005-07-14 Fuji Xerox Co., Ltd Systems and methods for creating and updating an interactive 3D visualization of media indices
US20050183041A1 (en) * 2004-02-12 2005-08-18 Fuji Xerox Co., Ltd. Systems and methods for creating and interactive 3D visualization of indexed media
US20050257151A1 (en) * 2004-05-13 2005-11-17 Peng Wu Method and apparatus for identifying selected portions of a video stream
US20060218192A1 (en) * 2004-08-31 2006-09-28 Gopalakrishnan Kumar C Method and System for Providing Information Services Related to Multimodal Inputs
US20070168413A1 (en) * 2003-12-05 2007-07-19 Sony Deutschland Gmbh Visualization and control techniques for multimedia digital content
US7296021B2 (en) 2004-05-21 2007-11-13 International Business Machines Corporation Method, system, and article to specify compound query, displaying visual indication includes a series of graphical bars specify weight relevance, ordered segments of unique colors where each segment length indicative of the extent of match of each object with one of search parameters
US20070286489A1 (en) * 2005-07-01 2007-12-13 International Business Machines Corporation Methods and apparatus for filtering video packets for large-scale video stream monitoring
US20080306921A1 (en) * 2000-01-31 2008-12-11 Kenneth Rothmuller Digital Media Management Apparatus and Methods
US20090157743A1 (en) * 2007-12-12 2009-06-18 Aten International Co., Ltd. Media file generation method and media playback method
US20090164904A1 (en) * 2007-12-21 2009-06-25 Yahoo! Inc. Blog-Based Video Summarization
US7672864B2 (en) 2004-01-09 2010-03-02 Ricoh Company Ltd. Generating and displaying level-of-interest values
US20100303365A1 (en) * 2009-05-29 2010-12-02 Min Zhang Methods and apparatus to monitor a multimedia presentation including multiple content windows
US20110035700A1 (en) * 2009-08-05 2011-02-10 Brian Meaney Multi-Operation User Interface Tool
US20110092251A1 (en) * 2004-08-31 2011-04-21 Gopalakrishnan Kumar C Providing Search Results from Visual Imagery
US20110093264A1 (en) * 2004-08-31 2011-04-21 Kumar Gopalakrishnan Providing Information Services Related to Multimodal Inputs
US20110093884A1 (en) * 2000-01-14 2011-04-21 Nds Limited. Advertisements in an end-user controlled playback environment
US20130166303A1 (en) * 2009-11-13 2013-06-27 Adobe Systems Incorporated Accessing media data using metadata repository
US20130290846A1 (en) * 2012-04-27 2013-10-31 Mobitv, Inc. Search-based navigation of media content
CN103399865A (en) * 2013-07-05 2013-11-20 华为技术有限公司 Method and device for multi-media file generation
US20140032562A1 (en) * 2012-07-26 2014-01-30 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and methods for user generated content indexing
US20140324907A1 (en) * 2005-11-29 2014-10-30 Aol Inc. Visually-Represented Results To Search Queries In Rich Media Content
US20150082338A1 (en) * 2000-03-28 2015-03-19 Compass Innovations, LLC Audiovisual Content Presentation Dependent On Metadata
US20150095749A1 (en) * 2013-09-27 2015-04-02 Nokia Corporation Visual Representation of a Character Identity and a Location Identity
US9691068B1 (en) * 2011-12-15 2017-06-27 Amazon Technologies, Inc. Public-domain analyzer
US9846696B2 (en) 2012-02-29 2017-12-19 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and methods for indexing multimedia content
US10289810B2 (en) 2013-08-29 2019-05-14 Telefonaktiebolaget Lm Ericsson (Publ) Method, content owner device, computer program, and computer program product for distributing content items to authorized users
US10311038B2 (en) 2013-08-29 2019-06-04 Telefonaktiebolaget Lm Ericsson (Publ) Methods, computer program, computer program product and indexing systems for indexing or updating index
US10445367B2 (en) 2013-05-14 2019-10-15 Telefonaktiebolaget Lm Ericsson (Publ) Search engine for textual content and non-textual content
US11082722B2 (en) * 2011-01-26 2021-08-03 Afterlive.tv Inc. Method and system for generating highlights from scored data streams
US20230009515A1 (en) * 2021-07-06 2023-01-12 Rovi Guides, Inc. Generating verified content profiles for user generated content
US20230222164A1 (en) * 2022-01-11 2023-07-13 Kyndryl, Inc. Autonomous webpage content summation

Families Citing this family (209)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11506575A (en) * 1995-03-07 1999-06-08 インターバル リサーチ コーポレイション Information selective storage system and method
US20030093790A1 (en) * 2000-03-28 2003-05-15 Logan James D. Audio and video program recording, editing and playback systems using metadata
US20060280437A1 (en) * 1999-01-27 2006-12-14 Gotuit Media Corp Methods and apparatus for vending and delivering the content of disk recordings
US6263507B1 (en) * 1996-12-05 2001-07-17 Interval Research Corporation Browser for use in navigating a body of information, with particular application to browsing information represented by audiovisual data
US5893062A (en) 1996-12-05 1999-04-06 Interval Research Corporation Variable rate video playback with synchronized audio
US7111009B1 (en) 1997-03-14 2006-09-19 Microsoft Corporation Interactive playlist generation using annotations
AU5926099A (en) 1998-09-15 2000-04-03 Microsoft Corporation Annotation creation and notification via electronic mail
US6956593B1 (en) 1998-09-15 2005-10-18 Microsoft Corporation User interface for creating, viewing and temporally positioning annotations for media content
JP2000207263A (en) * 1998-11-12 2000-07-28 Sony Corp Processor and method for information processing and providing medium
US7209942B1 (en) * 1998-12-28 2007-04-24 Kabushiki Kaisha Toshiba Information providing method and apparatus, and information reception apparatus
US6934461B1 (en) * 1999-01-05 2005-08-23 Interval Research Corporation Low attention recording, with particular application to social recording
JP2000253337A (en) * 1999-02-24 2000-09-14 Sony Corp Method and device for controlling screen, method and device for reproducing video, method and device for recording video information, and computer readable recording medium
US6262724B1 (en) * 1999-04-15 2001-07-17 Apple Computer, Inc. User interface for presenting media information
US7313808B1 (en) * 1999-07-08 2007-12-25 Microsoft Corporation Browsing continuous multimedia content
US7293280B1 (en) * 1999-07-08 2007-11-06 Microsoft Corporation Skimming continuous multimedia content
JP3424204B2 (en) * 1999-07-23 2003-07-07 インターナショナル・ビジネス・マシーンズ・コーポレーション Method and apparatus for accessing video content using trajectory of object
GB2354105A (en) * 1999-09-08 2001-03-14 Sony Uk Ltd System and method for navigating source content
US7155735B1 (en) 1999-10-08 2006-12-26 Vulcan Patents Llc System and method for the broadcast dissemination of time-ordered data
US6757682B1 (en) 2000-01-28 2004-06-29 Interval Research Corporation Alerting users to items of current interest
US6868440B1 (en) * 2000-02-04 2005-03-15 Microsoft Corporation Multi-level skimming of multimedia content using playlists
JP2001230994A (en) * 2000-02-15 2001-08-24 Fujitsu Ltd Data processor
US20060015925A1 (en) * 2000-03-28 2006-01-19 Gotuit Media Corp Sales presentation video on demand system
US7194186B1 (en) * 2000-04-21 2007-03-20 Vulcan Patents Llc Flexible marking of recording data by a recording unit
US6701014B1 (en) * 2000-06-14 2004-03-02 International Business Machines Corporation Method and apparatus for matching slides in video
US6882793B1 (en) 2000-06-16 2005-04-19 Yesvideo, Inc. Video processing system
US7490092B2 (en) 2000-07-06 2009-02-10 Streamsage, Inc. Method and system for indexing and searching timed media information based upon relevance intervals
EP1173013A3 (en) * 2000-07-14 2004-04-21 Sony Corporation Remote control device for recording/reproducing apparatus and video signal recording/reproducing apparatus
US8191103B2 (en) 2000-08-30 2012-05-29 Sony Corporation Real-time bookmarking of streaming media assets
US7254779B1 (en) * 2000-09-06 2007-08-07 Xanboo Inc. Customizable presentation environment
US6686838B1 (en) * 2000-09-06 2004-02-03 Xanboo Inc. Systems and methods for the automatic registration of devices
US6748375B1 (en) * 2000-09-07 2004-06-08 Microsoft Corporation System and method for content retrieval
CN100392749C (en) * 2000-09-08 2008-06-04 皇家菲利浦电子有限公司 Apparatus for reproducing information signal stored on storage medium
US7890989B1 (en) 2000-10-24 2011-02-15 Sony Corporation Automated context-sensitive updating on content in an audiovisual storage system
JP2002204441A (en) * 2000-10-26 2002-07-19 Sony Corp Information processing unit and information processing system
US8078967B2 (en) 2000-12-01 2011-12-13 Jlb Ventures Llc Method and apparatus for virtual editing of multimedia presentations
US7177531B2 (en) * 2000-12-05 2007-02-13 Matsushita Electric Industrial Co., Ltd. Record and playback apparatus and record medium
US7401351B2 (en) * 2000-12-14 2008-07-15 Fuji Xerox Co., Ltd. System and method for video navigation and client side indexing
US7007243B2 (en) 2000-12-20 2006-02-28 Eastman Kodak Company Method and apparatus for producing digital images with embedded image capture location icons
US7020848B2 (en) * 2000-12-20 2006-03-28 Eastman Kodak Company Comprehensive, multi-dimensional graphical user interface using picture metadata for navigating and retrieving pictures in a picture database
US20020083473A1 (en) * 2000-12-21 2002-06-27 Philips Electronics North America Corporation System and method for accessing a multimedia summary of a video program
US20070300258A1 (en) * 2001-01-29 2007-12-27 O'connor Daniel Methods and systems for providing media assets over a network
JP4188568B2 (en) * 2001-02-06 2008-11-26 パイオニア株式会社 Information reproducing apparatus and information editing method
US20020120833A1 (en) * 2001-02-15 2002-08-29 Inventec Corporation Method for automatic obtaining the ID number of items of a volume control program
JP2002259720A (en) * 2001-03-02 2002-09-13 Internatl Business Mach Corp <Ibm> Contents summarizing system, image summarizing system, user terminal unit, summary image producing method, summary image receiving method, and program
EP1251515A1 (en) * 2001-04-19 2002-10-23 Koninklijke Philips Electronics N.V. Method and system for selecting a position in an image sequence
US20050005308A1 (en) * 2002-01-29 2005-01-06 Gotuit Video, Inc. Methods and apparatus for recording and replaying sports broadcasts
US20030009371A1 (en) * 2001-07-03 2003-01-09 Ravi Gauba Interactive decision-making scenarios in an audio/video broadcast
US20030028871A1 (en) * 2001-07-20 2003-02-06 Annie Wang Behavior profile system and method
US8515773B2 (en) 2001-08-01 2013-08-20 Sony Corporation System and method for enabling distribution and brokering of content information
US20030025720A1 (en) * 2001-08-03 2003-02-06 Clement Lau System and method for common interest analysis among multiple users
US7747943B2 (en) * 2001-09-07 2010-06-29 Microsoft Corporation Robust anchoring of annotations to content
US20030074447A1 (en) * 2001-10-16 2003-04-17 Rafey Richter A. Intuitive mapping between explicit and implicit personalization
CN1269105C (en) * 2001-10-31 2006-08-09 皇家飞利浦电子股份有限公司 Method of and system for transcribing dictations in text files and for revising the text
US20030112276A1 (en) * 2001-12-19 2003-06-19 Clement Lau User augmentation of content
US7337455B2 (en) * 2001-12-31 2008-02-26 Koninklijke Philips Electronics N.V. Method, apparatus, and program for evolving algorithms for detecting content in information streams
JP3772117B2 (en) * 2002-01-18 2006-05-10 ソニー株式会社 Information signal processing apparatus and information signal processing method
US7739601B1 (en) * 2002-01-23 2010-06-15 Microsoft Corporation Media authoring and presentation
US20070113250A1 (en) * 2002-01-29 2007-05-17 Logan James D On demand fantasy sports systems and methods
US7243301B2 (en) 2002-04-10 2007-07-10 Microsoft Corporation Common annotation framework
US7568151B2 (en) * 2002-06-27 2009-07-28 Microsoft Corporation Notification of activity around documents
US7587318B2 (en) * 2002-09-12 2009-09-08 Broadcom Corporation Correlating video images of lip movements with audio signals to improve speech recognition
US20040059996A1 (en) * 2002-09-24 2004-03-25 Fasciano Peter J. Exhibition of digital media assets from a digital media asset management system to facilitate creative story generation
DE10297802B4 (en) * 2002-09-30 2011-05-19 Adobe Systems, Inc., San Jose Method, storage medium and system for searching a collection of media objects
EP1584048A1 (en) * 2003-01-06 2005-10-12 Koninklijke Philips Electronics N.V. Method and apparatus for similar video content hopping
EP1463258A1 (en) * 2003-03-28 2004-09-29 Mobile Integrated Solutions Limited A system and method for transferring data over a wireless communications network
US7233316B2 (en) 2003-05-01 2007-06-19 Thomson Licensing Multimedia user interface
JP2004364234A (en) * 2003-05-15 2004-12-24 Pioneer Electronic Corp Broadcast program content menu creation apparatus and method
US20040230910A1 (en) * 2003-05-16 2004-11-18 Brian Lin Assistant editing display method for media clips
JP4235490B2 (en) * 2003-06-04 2009-03-11 パイオニア株式会社 Music program content menu creation apparatus and method
US7512622B2 (en) * 2003-06-11 2009-03-31 Yahoo! Inc. Method and apparatus for organizing and playing data
US20070118812A1 (en) * 2003-07-15 2007-05-24 Kaleidescope, Inc. Masking for presenting differing display formats for media streams
US20050044561A1 (en) * 2003-08-20 2005-02-24 Gotuit Audio, Inc. Methods and apparatus for identifying program segments by detecting duplicate signal patterns
US20050071214A1 (en) * 2003-09-25 2005-03-31 Kover Arthur J. Method and apparatus for obtaining web-based advertising research data
US7596255B2 (en) * 2003-11-26 2009-09-29 Ge Medical Systems Information Technologies, Inc. Image navigation system and method
US20050154987A1 (en) * 2004-01-14 2005-07-14 Isao Otsuka System and method for recording and reproducing multimedia
JP4426853B2 (en) * 2004-01-19 2010-03-03 オリンパス株式会社 Information display program, information display method, information display apparatus, and recording medium
US7447331B2 (en) * 2004-02-24 2008-11-04 International Business Machines Corporation System and method for generating a viewable video index for low bandwidth applications
US20060031879A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of news-related broadcasted or streamed multimedia content
US20060031916A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of broadcasted or streamed multimedia content
US20060031885A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of music-related broadcasted or streamed multimedia content
US7908339B2 (en) * 2004-06-03 2011-03-15 Maxsp Corporation Transaction based virtual file system optimized for high-latency network connections
US8812613B2 (en) * 2004-06-03 2014-08-19 Maxsp Corporation Virtual application manager
US9357031B2 (en) 2004-06-03 2016-05-31 Microsoft Technology Licensing, Llc Applications as a service
US7664834B2 (en) * 2004-07-09 2010-02-16 Maxsp Corporation Distributed operating system management
JP4123209B2 (en) * 2004-09-07 2008-07-23 ソニー株式会社 Video material management apparatus and method, recording medium, and program
US8768844B2 (en) 2004-10-06 2014-07-01 Sony Corporation Method and system for content sharing and authentication between multiple devices
JP4649944B2 (en) * 2004-10-20 2011-03-16 富士ゼロックス株式会社 Moving image processing apparatus, moving image processing method, and program
US7783106B2 (en) * 2004-11-12 2010-08-24 Fuji Xerox Co., Ltd. Video segmentation combining similarity analysis and classification
US7624086B2 (en) * 2005-03-04 2009-11-24 Maxsp Corporation Pre-install compliance system
US7512584B2 (en) * 2005-03-04 2009-03-31 Maxsp Corporation Computer hardware and software diagnostic and report system
US8589323B2 (en) 2005-03-04 2013-11-19 Maxsp Corporation Computer hardware and software diagnostic and report system incorporating an expert system and agents
US8234238B2 (en) * 2005-03-04 2012-07-31 Maxsp Corporation Computer hardware and software diagnostic and report system
US7689631B2 (en) * 2005-05-31 2010-03-30 Sap, Ag Method for utilizing audience-specific metadata
US8089563B2 (en) * 2005-06-17 2012-01-03 Fuji Xerox Co., Ltd. Method and system for analyzing fixed-camera video via the selection, visualization, and interaction with storyboard keyframes
US7996771B2 (en) * 2005-06-17 2011-08-09 Fuji Xerox Co., Ltd. Methods and interfaces for event timeline and logs of video streams
US7623677B2 (en) * 2005-06-17 2009-11-24 Fuji Xerox Co., Ltd. Methods and interfaces for visualizing activity across video frames in an action keyframe
US20070016611A1 (en) * 2005-07-13 2007-01-18 Ulead Systems, Inc. Preview method for seeking media content
US7487206B2 (en) * 2005-07-15 2009-02-03 International Business Machines Corporation Method for providing load diffusion in data stream correlations
US20070027808A1 (en) * 2005-07-29 2007-02-01 Microsoft Corporation Strategies for queuing events for subsequent processing
GB2430101A (en) * 2005-09-09 2007-03-14 Mitsubishi Electric Inf Tech Applying metadata for video navigation
US20070185857A1 (en) * 2006-01-23 2007-08-09 International Business Machines Corporation System and method for extracting salient keywords for videos
US7720258B1 (en) 2006-01-26 2010-05-18 Adobe Systems Incorporated Structured comparison of objects from similar images
US7706577B1 (en) 2006-01-26 2010-04-27 Adobe Systems Incorporated Exporting extracted faces
US7716157B1 (en) 2006-01-26 2010-05-11 Adobe Systems Incorporated Searching images with extracted objects
US7813557B1 (en) 2006-01-26 2010-10-12 Adobe Systems Incorporated Tagging detected objects
US8259995B1 (en) 2006-01-26 2012-09-04 Adobe Systems Incorporated Designating a tag icon
US7978936B1 (en) * 2006-01-26 2011-07-12 Adobe Systems Incorporated Indicating a correspondence between an image and an object
US7813526B1 (en) 2006-01-26 2010-10-12 Adobe Systems Incorporated Normalizing detected objects
US7636450B1 (en) 2006-01-26 2009-12-22 Adobe Systems Incorporated Displaying detected objects to indicate grouping
US7694885B1 (en) 2006-01-26 2010-04-13 Adobe Systems Incorporated Indicating a tag with visual data
US20070204238A1 (en) * 2006-02-27 2007-08-30 Microsoft Corporation Smart Video Presentation
US7735101B2 (en) 2006-03-28 2010-06-08 Cisco Technology, Inc. System allowing users to embed comments at specific points in time into media presentation
US20080036917A1 (en) * 2006-04-07 2008-02-14 Mark Pascarella Methods and systems for generating and delivering navigatable composite videos
US8117246B2 (en) * 2006-04-17 2012-02-14 Microsoft Corporation Registering, transfering, and acting on event metadata
US20070256008A1 (en) * 2006-04-26 2007-11-01 Bedingfield James C Sr Methods, systems, and computer program products for managing audio information
US8701005B2 (en) * 2006-04-26 2014-04-15 At&T Intellectual Property I, Lp Methods, systems, and computer program products for managing video information
US20070256007A1 (en) * 2006-04-26 2007-11-01 Bedingfield James C Sr Methods, systems, and computer program products for managing information by annotating a captured information object
US7548937B2 (en) * 2006-05-04 2009-06-16 International Business Machines Corporation System and method for scalable processing of multi-way data stream correlations
US7954049B2 (en) 2006-05-15 2011-05-31 Microsoft Corporation Annotating multimedia files along a timeline
US8811396B2 (en) * 2006-05-24 2014-08-19 Maxsp Corporation System for and method of securing a network utilizing credentials
US8898319B2 (en) 2006-05-24 2014-11-25 Maxsp Corporation Applications and services as a bundle
US20070276852A1 (en) * 2006-05-25 2007-11-29 Microsoft Corporation Downloading portions of media files
US8140530B2 (en) * 2006-08-03 2012-03-20 Nec Corporation Similarity calculation device and information search device
US7956849B2 (en) 2006-09-06 2011-06-07 Apple Inc. Video manager for portable multifunction device
US8954851B2 (en) * 2006-09-15 2015-02-10 Microsoft Corporation Adding video effects for video enabled applications
US9317506B2 (en) * 2006-09-22 2016-04-19 Microsoft Technology Licensing, Llc Accelerated data transfer using common prior data segments
US20080077622A1 (en) * 2006-09-22 2008-03-27 Keith Robert O Method of and apparatus for managing data utilizing configurable policies and schedules
US7840514B2 (en) * 2006-09-22 2010-11-23 Maxsp Corporation Secure virtual private network utilizing a diagnostics policy and diagnostics engine to establish a secure network connection
US7792868B2 (en) * 2006-11-10 2010-09-07 Microsoft Corporation Data object linking and browsing tool
US7827490B2 (en) * 2006-11-30 2010-11-02 Microsoft Corporation Media state user interface
US8423821B1 (en) 2006-12-21 2013-04-16 Maxsp Corporation Virtual recovery server
US7844686B1 (en) 2006-12-21 2010-11-30 Maxsp Corporation Warm standby appliance
US7953640B2 (en) * 2007-04-04 2011-05-31 Disney Enterprises, Inc. Method and system for determining a value of a portion of content
US8091039B2 (en) * 2007-04-13 2012-01-03 Apple Inc. Authoring interface which distributes composited elements about the display
US8874468B2 (en) * 2007-04-20 2014-10-28 Google Inc. Media advertising
US9438860B2 (en) * 2007-06-26 2016-09-06 Verizon Patent And Licensing Inc. Method and system for filtering advertisements in a media stream
US8175418B1 (en) 2007-10-26 2012-05-08 Maxsp Corporation Method of and system for enhanced data storage
US8645515B2 (en) 2007-10-26 2014-02-04 Maxsp Corporation Environment manager
US8307239B1 (en) 2007-10-26 2012-11-06 Maxsp Corporation Disaster recovery appliance
US10216761B2 (en) * 2008-03-04 2019-02-26 Oath Inc. Generating congruous metadata for multimedia
US10552384B2 (en) 2008-05-12 2020-02-04 Blackberry Limited Synchronizing media files available from multiple sources
US8706690B2 (en) 2008-05-12 2014-04-22 Blackberry Limited Systems and methods for space management in file systems
US8140550B2 (en) * 2008-08-20 2012-03-20 Satyam Computer Services Limited Of Mayfair Centre System and method for bounded analysis of multimedia using multiple correlations
US9442933B2 (en) * 2008-12-24 2016-09-13 Comcast Interactive Media, Llc Identification of segments within audio, video, and multimedia items
US8713016B2 (en) 2008-12-24 2014-04-29 Comcast Interactive Media, Llc Method and apparatus for organizing segments of media assets and determining relevance of segments to a query
US11531668B2 (en) * 2008-12-29 2022-12-20 Comcast Interactive Media, Llc Merging of multiple data sets
US8176043B2 (en) 2009-03-12 2012-05-08 Comcast Interactive Media, Llc Ranking search results
US10705701B2 (en) 2009-03-16 2020-07-07 Apple Inc. Device, method, and graphical user interface for moving a current position in content at a variable scrubbing rate
US8533223B2 (en) * 2009-05-12 2013-09-10 Comcast Interactive Media, LLC. Disambiguation and tagging of entities
JP2010288015A (en) 2009-06-10 2010-12-24 Sony Corp Information processing device, information processing method, and information processing program
US9892730B2 (en) 2009-07-01 2018-02-13 Comcast Interactive Media, Llc Generating topic-specific language models
US9542489B2 (en) * 2009-07-16 2017-01-10 Bluefin Labs, Inc. Estimating social interest in time-based media
US9069884B2 (en) 2009-09-08 2015-06-30 International Business Machines Corporation Processing special attributes within a file
US8856636B1 (en) * 2009-09-22 2014-10-07 Adobe Systems Incorporated Methods and systems for trimming video footage
US8572488B2 (en) * 2010-03-29 2013-10-29 Avid Technology, Inc. Spot dialog editor
US8423555B2 (en) 2010-07-09 2013-04-16 Comcast Cable Communications, Llc Automatic segmentation of video
US10324605B2 (en) 2011-02-16 2019-06-18 Apple Inc. Media-editing application with novel editing tools
EP2659482B1 (en) * 2010-12-30 2015-12-09 Dolby Laboratories Licensing Corporation Ranking representative segments in media data
US8886015B2 (en) 2011-01-28 2014-11-11 Apple Inc. Efficient media import
US9026909B2 (en) 2011-02-16 2015-05-05 Apple Inc. Keyword list view
US9997196B2 (en) 2011-02-16 2018-06-12 Apple Inc. Retiming media presentations
US11747972B2 (en) 2011-02-16 2023-09-05 Apple Inc. Media-editing application with novel editing tools
US9288511B2 (en) 2011-02-18 2016-03-15 Futurewei Technologies, Inc. Methods and apparatus for media navigation
US10467289B2 (en) 2011-08-02 2019-11-05 Comcast Cable Communications, Llc Segmentation of video according to narrative theme
US9536564B2 (en) 2011-09-20 2017-01-03 Apple Inc. Role-facilitated editing operations
US20130073960A1 (en) 2011-09-20 2013-03-21 Aaron M. Eppolito Audio meters and parameter controls
US20130091421A1 (en) * 2011-10-11 2013-04-11 International Business Machines Corporation Time relevance within a soft copy document or media object
US9483110B2 (en) 2011-11-07 2016-11-01 International Business Machines Corporation Adaptive media file rewind
US9767194B2 (en) * 2011-11-07 2017-09-19 International Business Machines Corporation Media file abbreviation retrieval
JP5980604B2 (en) * 2012-07-18 2016-08-31 オリンパス株式会社 Endoscope system
US20140089467A1 (en) * 2012-09-27 2014-03-27 Andre Beck Content stream delivery using pre-loaded segments
JP2014126600A (en) * 2012-12-25 2014-07-07 Panasonic Corp Voice recognition device, voice recognition method and television
US8537983B1 (en) * 2013-03-08 2013-09-17 Noble Systems Corporation Multi-component viewing tool for contact center agents
US9495365B2 (en) * 2013-03-15 2016-11-15 International Business Machines Corporation Identifying key differences between related content from different mediums
US9804729B2 (en) 2013-03-15 2017-10-31 International Business Machines Corporation Presenting key differences between related content from different mediums
US9158435B2 (en) * 2013-03-15 2015-10-13 International Business Machines Corporation Synchronizing progress between related content from different mediums
JP6117621B2 (en) * 2013-06-05 2017-04-19 ソニー株式会社 Information processing apparatus, information processing method, and information processing program
TW201513095A (en) * 2013-09-23 2015-04-01 Hon Hai Prec Ind Co Ltd Audio or video files processing system, device and method
US9213903B1 (en) 2014-07-07 2015-12-15 Google Inc. Method and system for cluster-based video monitoring and event categorization
US9449229B1 (en) 2014-07-07 2016-09-20 Google Inc. Systems and methods for categorizing motion event candidates
US9501915B1 (en) 2014-07-07 2016-11-22 Google Inc. Systems and methods for analyzing a video stream
US10127783B2 (en) 2014-07-07 2018-11-13 Google Llc Method and device for processing motion events
US9082018B1 (en) 2014-09-30 2015-07-14 Google Inc. Method and system for retroactively changing a display characteristic of event indicators on an event timeline
US10140827B2 (en) 2014-07-07 2018-11-27 Google Llc Method and system for processing motion event notifications
CN110072131A (en) 2014-09-02 2019-07-30 苹果公司 Music user interface
USD782495S1 (en) 2014-10-07 2017-03-28 Google Inc. Display screen or portion thereof with graphical user interface
US9361011B1 (en) 2015-06-14 2016-06-07 Google Inc. Methods and systems for presenting multiple live video feeds in a user interface
US11699266B2 (en) * 2015-09-02 2023-07-11 Interdigital Ce Patent Holdings, Sas Method, apparatus and system for facilitating navigation in an extended scene
US10506237B1 (en) 2016-05-27 2019-12-10 Google Llc Methods and devices for dynamic adaptation of encoding bitrate for video streaming
US10957171B2 (en) 2016-07-11 2021-03-23 Google Llc Methods and systems for providing event alerts
US10380429B2 (en) 2016-07-11 2019-08-13 Google Llc Methods and systems for person detection in a video feed
US10192415B2 (en) 2016-07-11 2019-01-29 Google Llc Methods and systems for providing intelligent alerts for events
US10992795B2 (en) 2017-05-16 2021-04-27 Apple Inc. Methods and interfaces for home media control
US11431836B2 (en) 2017-05-02 2022-08-30 Apple Inc. Methods and interfaces for initiating media playback
US10928980B2 (en) 2017-05-12 2021-02-23 Apple Inc. User interfaces for playing and managing audio items
US20220279063A1 (en) 2017-05-16 2022-09-01 Apple Inc. Methods and interfaces for home media control
CN111343060B (en) 2017-05-16 2022-02-11 苹果公司 Method and interface for home media control
US10410086B2 (en) 2017-05-30 2019-09-10 Google Llc Systems and methods of person recognition in video streams
US11783010B2 (en) 2017-05-30 2023-10-10 Google Llc Systems and methods of person recognition in video streams
US10664688B2 (en) 2017-09-20 2020-05-26 Google Llc Systems and methods of detecting and responding to a visitor to a smart home environment
US11134227B2 (en) 2017-09-20 2021-09-28 Google Llc Systems and methods of presenting appropriate actions for responding to a visitor to a smart home environment
US11153619B2 (en) 2018-07-02 2021-10-19 International Business Machines Corporation Cognitively derived multimedia streaming preferences
KR20230039775A (en) 2019-05-31 2023-03-21 애플 인크. User interfaces for audio media control
US11010121B2 (en) 2019-05-31 2021-05-18 Apple Inc. User interfaces for audio media control
US11113229B2 (en) * 2019-06-03 2021-09-07 International Business Machines Corporation Providing a continuation point for a user to recommence consuming content
US11893795B2 (en) 2019-12-09 2024-02-06 Google Llc Interacting with visitors of a connected home environment
US11442609B1 (en) * 2020-04-08 2022-09-13 Gopro, Inc. Interface for setting speed and direction of video playback
US11392291B2 (en) 2020-09-25 2022-07-19 Apple Inc. Methods and interfaces for media control with dynamic feedback
US11823713B1 (en) * 2022-10-03 2023-11-21 Bolt-On Ip Solutions, Llc System and method for editing an audio stream

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5136655A (en) 1990-03-26 1992-08-04 Hewlett-Pacard Company Method and apparatus for indexing and retrieving audio-video data
US5579471A (en) * 1992-11-09 1996-11-26 International Business Machines Corporation Image query system and method
US5655058A (en) 1994-04-12 1997-08-05 Xerox Corporation Segmentation of audio data for indexing of conversational speech for real-time or postprocessing applications
US5493677A (en) * 1994-06-08 1996-02-20 Systems Research & Applications Corporation Generation, archiving, and retrieval of digital images with evoked suggestion-set captions and natural language interface
US5664227A (en) 1994-10-14 1997-09-02 Carnegie Mellon University System and method for skimming digital audio/video data
US5708767A (en) 1995-02-03 1998-01-13 The Trustees Of Princeton University Method and apparatus for video browsing based on content and structure
US5729471A (en) * 1995-03-31 1998-03-17 The Regents Of The University Of California Machine dynamic selection of one video camera/image of a scene from multiple video cameras/images of the scene in accordance with a particular perspective on the scene, an object in the scene, or an event in the scene
US5987459A (en) * 1996-03-15 1999-11-16 Regents Of The University Of Minnesota Image and document management system for content-based retrieval
US5893110A (en) * 1996-08-16 1999-04-06 Silicon Graphics, Inc. Browser driven user interface to a media asset database
US6055543A (en) * 1997-11-21 2000-04-25 Verano File wrapper containing cataloging information for content searching across multiple platforms

Cited By (64)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8995767B2 (en) 1997-12-22 2015-03-31 Ricoh Company, Ltd. Multimedia visualization and integration environment
US20040175036A1 (en) * 1997-12-22 2004-09-09 Ricoh Company, Ltd. Multimedia visualization and integration environment
US20040103372A1 (en) * 1997-12-22 2004-05-27 Ricoh Company, Ltd. Multimedia visualization and integration environment
US8739040B2 (en) * 1997-12-22 2014-05-27 Ricoh Company, Ltd. Multimedia visualization and integration environment
US6782049B1 (en) * 1999-01-29 2004-08-24 Hewlett-Packard Development Company, L.P. System for selecting a keyframe to represent a video
US7643657B2 (en) 1999-01-29 2010-01-05 Hewlett-Packard Development Company, L.P. System for selecting a keyframe to represent a video
US20050002452A1 (en) * 1999-01-29 2005-01-06 Frederic Dufaux System for selecting a keyframe to represent a video
US20110093884A1 (en) * 2000-01-14 2011-04-21 Nds Limited. Advertisements in an end-user controlled playback environment
US8732750B2 (en) * 2000-01-14 2014-05-20 Cisco Technology, Inc. Advertisements in an end-user controlled playback environment
US20080306921A1 (en) * 2000-01-31 2008-12-11 Kenneth Rothmuller Digital Media Management Apparatus and Methods
US8229931B2 (en) * 2000-01-31 2012-07-24 Adobe Systems Incorporated Digital media management apparatus and methods
USRE38609E1 (en) * 2000-02-28 2004-10-05 Webex Communications, Inc. On-demand presentation graphical user interface
US20150082338A1 (en) * 2000-03-28 2015-03-19 Compass Innovations, LLC Audiovisual Content Presentation Dependent On Metadata
US10313714B2 (en) * 2000-03-28 2019-06-04 Tivo Solutions Inc. Audiovisual content presentation dependent on metadata
US6711587B1 (en) 2000-09-05 2004-03-23 Hewlett-Packard Development Company, L.P. Keyframe selection to represent a video
EP1376584A3 (en) * 2002-06-19 2004-12-22 Microsoft Corporation System and method for automatically generating video cliplets from digital video
US8238718B2 (en) 2002-06-19 2012-08-07 Microsoft Corporaton System and method for automatically generating video cliplets from digital video
US20070168413A1 (en) * 2003-12-05 2007-07-19 Sony Deutschland Gmbh Visualization and control techniques for multimedia digital content
US8209623B2 (en) 2003-12-05 2012-06-26 Sony Deutschland Gmbh Visualization and control techniques for multimedia digital content
US7672864B2 (en) 2004-01-09 2010-03-02 Ricoh Company Ltd. Generating and displaying level-of-interest values
US7079142B2 (en) 2004-01-14 2006-07-18 Fuji Xerox Co., Ltd. Systems and methods for creating and updating an interactive 3D visualization of media indices
US20050151737A1 (en) * 2004-01-14 2005-07-14 Fuji Xerox Co., Ltd Systems and methods for creating and updating an interactive 3D visualization of media indices
US7340678B2 (en) 2004-02-12 2008-03-04 Fuji Xerox Co., Ltd. Systems and methods for creating an interactive 3D visualization of indexed media
US20080104546A1 (en) * 2004-02-12 2008-05-01 Fuji Xerox Co., Ltd. Systems and methods for creating an interactive 3d visualization of indexed media
US20050183041A1 (en) * 2004-02-12 2005-08-18 Fuji Xerox Co., Ltd. Systems and methods for creating and interactive 3D visualization of indexed media
US7802188B2 (en) * 2004-05-13 2010-09-21 Hewlett-Packard Development Company, L.P. Method and apparatus for identifying selected portions of a video stream
US20050257151A1 (en) * 2004-05-13 2005-11-17 Peng Wu Method and apparatus for identifying selected portions of a video stream
US7296021B2 (en) 2004-05-21 2007-11-13 International Business Machines Corporation Method, system, and article to specify compound query, displaying visual indication includes a series of graphical bars specify weight relevance, ordered segments of unique colors where each segment length indicative of the extent of match of each object with one of search parameters
US7853582B2 (en) * 2004-08-31 2010-12-14 Gopalakrishnan Kumar C Method and system for providing information services related to multimodal inputs
US9639633B2 (en) 2004-08-31 2017-05-02 Intel Corporation Providing information services related to multimodal inputs
US20110092251A1 (en) * 2004-08-31 2011-04-21 Gopalakrishnan Kumar C Providing Search Results from Visual Imagery
US20110093264A1 (en) * 2004-08-31 2011-04-21 Kumar Gopalakrishnan Providing Information Services Related to Multimodal Inputs
US20060218192A1 (en) * 2004-08-31 2006-09-28 Gopalakrishnan Kumar C Method and System for Providing Information Services Related to Multimodal Inputs
US8370323B2 (en) 2004-08-31 2013-02-05 Intel Corporation Providing information services related to multimodal inputs
US20090080777A1 (en) * 2005-07-01 2009-03-26 International Business Machines Corporation Methods and Apparatus for Filtering Video Packets for Large-Scale Video Stream Monitoring
US7912284B2 (en) * 2005-07-01 2011-03-22 International Business Machines Corporation Methods and apparatus for filtering video packets for large-scale video stream monitoring
US20070286489A1 (en) * 2005-07-01 2007-12-13 International Business Machines Corporation Methods and apparatus for filtering video packets for large-scale video stream monitoring
US7545978B2 (en) * 2005-07-01 2009-06-09 International Business Machines Corporation Methods and apparatus for filtering video packets for large-scale video stream monitoring
US20140324907A1 (en) * 2005-11-29 2014-10-30 Aol Inc. Visually-Represented Results To Search Queries In Rich Media Content
US20090157743A1 (en) * 2007-12-12 2009-06-18 Aten International Co., Ltd. Media file generation method and media playback method
US20090164904A1 (en) * 2007-12-21 2009-06-25 Yahoo! Inc. Blog-Based Video Summarization
US9535988B2 (en) * 2007-12-21 2017-01-03 Yahoo! Inc. Blog-based video summarization
US20100303365A1 (en) * 2009-05-29 2010-12-02 Min Zhang Methods and apparatus to monitor a multimedia presentation including multiple content windows
US20110035700A1 (en) * 2009-08-05 2011-02-10 Brian Meaney Multi-Operation User Interface Tool
US20130166303A1 (en) * 2009-11-13 2013-06-27 Adobe Systems Incorporated Accessing media data using metadata repository
US11082722B2 (en) * 2011-01-26 2021-08-03 Afterlive.tv Inc. Method and system for generating highlights from scored data streams
US9691068B1 (en) * 2011-12-15 2017-06-27 Amazon Technologies, Inc. Public-domain analyzer
US9846696B2 (en) 2012-02-29 2017-12-19 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and methods for indexing multimedia content
US11789992B2 (en) * 2012-04-27 2023-10-17 Tivo Corporation Search-based navigation of media content
US20130290846A1 (en) * 2012-04-27 2013-10-31 Mobitv, Inc. Search-based navigation of media content
US9785639B2 (en) * 2012-04-27 2017-10-10 Mobitv, Inc. Search-based navigation of media content
US10628477B2 (en) 2012-04-27 2020-04-21 Mobitv, Inc. Search-based navigation of media content
US9633015B2 (en) * 2012-07-26 2017-04-25 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and methods for user generated content indexing
US20140032562A1 (en) * 2012-07-26 2014-01-30 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and methods for user generated content indexing
US10445367B2 (en) 2013-05-14 2019-10-15 Telefonaktiebolaget Lm Ericsson (Publ) Search engine for textual content and non-textual content
CN103399865A (en) * 2013-07-05 2013-11-20 华为技术有限公司 Method and device for multi-media file generation
US10311038B2 (en) 2013-08-29 2019-06-04 Telefonaktiebolaget Lm Ericsson (Publ) Methods, computer program, computer program product and indexing systems for indexing or updating index
US10289810B2 (en) 2013-08-29 2019-05-14 Telefonaktiebolaget Lm Ericsson (Publ) Method, content owner device, computer program, and computer program product for distributing content items to authorized users
US9110869B2 (en) * 2013-09-27 2015-08-18 Nokia Technologies Oy Visual representation of a character identity and a location identity
US20150095749A1 (en) * 2013-09-27 2015-04-02 Nokia Corporation Visual Representation of a Character Identity and a Location Identity
US20230009515A1 (en) * 2021-07-06 2023-01-12 Rovi Guides, Inc. Generating verified content profiles for user generated content
US11615139B2 (en) * 2021-07-06 2023-03-28 Rovi Guides, Inc. Generating verified content profiles for user generated content
US20230222164A1 (en) * 2022-01-11 2023-07-13 Kyndryl, Inc. Autonomous webpage content summation
US11860946B2 (en) * 2022-01-11 2024-01-02 Kyndryl, Inc. Autonomous webpage content summation

Also Published As

Publication number Publication date
US6366296B1 (en) 2002-04-02
JP2000090121A (en) 2000-03-31

Similar Documents

Publication Publication Date Title
US6366296B1 (en) Media browser using multimodal analysis
US10031649B2 (en) Automated content detection, analysis, visual synthesis and repurposing
US7046914B2 (en) Automatic content analysis and representation of multimedia presentations
US7594177B2 (en) System and method for video browsing using a cluster index
US5805733A (en) Method and system for detecting scenes and summarizing video sequences
US7945142B2 (en) Audio/visual editing tool
US6571054B1 (en) Method for creating and utilizing electronic image book and recording medium having recorded therein a program for implementing the method
CN112740713B (en) Method for providing key time in multimedia content and electronic device thereof
US5819103A (en) Information recording/reproducing apparatus and method
US7702014B1 (en) System and method for video production
US9100616B2 (en) Relational display of images
US20050257151A1 (en) Method and apparatus for identifying selected portions of a video stream
US20090158323A1 (en) Method and apparatus for video navigation
US7099894B2 (en) Multimedia information collection control apparatus and method
KR20140139859A (en) Method and apparatus for user interface for multimedia content search
KR101440168B1 (en) Method for creating a new summary of an audiovisual document that already includes a summary and reports and a receiver that can implement said method
JP3579111B2 (en) Information processing equipment
US20040056881A1 (en) Image retrieval system
Girgensohn et al. Facilitating Video Access by Visualizing Automatic Analysis.
AU3724497A (en) Digital video system having a data base of coded data for digital audio and ideo information
JPH0520367A (en) Index generating system
JP2004234683A (en) Information processor and information processing method
Budlong et al. Multimedia Information Extraction
Smith et al. Visualization Techniques

Legal Events

Date Code Title Description
AS Assignment

Owner name: BANK ONE, NA, AS ADMINISTRATIVE AGENT, ILLINOIS

Free format text: SECURITY AGREEMENT;ASSIGNOR:XEROX CORPORATION;REEL/FRAME:013111/0001

Effective date: 20020621

Owner name: BANK ONE, NA, AS ADMINISTRATIVE AGENT,ILLINOIS

Free format text: SECURITY AGREEMENT;ASSIGNOR:XEROX CORPORATION;REEL/FRAME:013111/0001

Effective date: 20020621

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION

AS Assignment

Owner name: NATIONAL INSTITUTES OF HEALTH (NIH), U.S. DEPT. OF

Free format text: CONFIRMATORY LICENSE;ASSIGNOR:SALK INSTITUTE FOR BIOLOGICAL STUDIES;REEL/FRAME:024793/0769

Effective date: 20010608

AS Assignment

Owner name: XEROX CORPORATION, CONNECTICUT

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JPMORGAN CHASE BANK, N.A. AS SUCCESSOR-IN-INTEREST ADMINISTRATIVE AGENT AND COLLATERAL AGENT TO BANK ONE, N.A.;REEL/FRAME:061388/0388

Effective date: 20220822