WO2002021843A2 - System to index/summarize audio/video content - Google Patents
System to index/summarize audio/video content Download PDFInfo
- Publication number
- WO2002021843A2 WO2002021843A2 PCT/EP2001/009974 EP0109974W WO0221843A2 WO 2002021843 A2 WO2002021843 A2 WO 2002021843A2 EP 0109974 W EP0109974 W EP 0109974W WO 0221843 A2 WO0221843 A2 WO 0221843A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- content material
- production
- source
- ancillary
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/64—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Definitions
- This invention relates to the field of consumer electronics, and in particular to a system that facilitates the indexing and summarizing of audio/video content for efficient search and retrieval of select content.
- the BNN allows the consumer to enter search words, with which the BNN sorts the story segments by the number of keywords in each story segment that match the search words. Based upon the frequency of occurrences of matching keywords, the user selects stories of interest. Similar search and retrieval techniques are becoming common in the art. For example, conventional text searching techniques can be applied to a computer based television guide, so that a person may search for a particular show title, a particular performer, shows of a particular type, and the like.
- indexing and search techniques are also being developed for recorded entertainment material, such as audio and video CDs and DVDs. Users will be able to search, for example, for a particular scene by specifying a performer's name and a characterization of the scene, such as "monologue, John Smith". In response, the search device will present one or more scenes containing John Smith performing a monologue.
- any closed-caption text is also used to identify and categorize scenes. Although these techniques are proving to be somewhat effective, they rely heavily on the content of the material, such as the images or voices in each scene, to determine an appropriate set of indexing parameters to characterize the material.
- the MPEG-7 standard addresses the need for effective indexing and search capabilities, and calls for a "Multimedia Content Description Interface" that is intended to standardize a set of description schemes and descriptors, a description definition language, and a scheme for coding the description.
- the MPEG-7 standard calls for the ability to associate descriptive information within video streams at various stages of video production, including pre- and post-production scripts, information captured or annotated during shooting, and post-production edit lists. By adding this information during the production of the video material, the quality and effectiveness of the annotations is expected to be substantially improved, compared to an after-production annotation of material in a video archive.
- This production information includes, for example, the camera settings used during the collection of the content material.
- Other production information includes sound controls, scene identifiers, source identifiers, instructions that are communicated to the staff that produces the content material, and so on. Instructions from a director to each camera operator, for example, can provide insight into the content of the subsequent images from the cameras. In like manner, automatically generated instructions from automated camera systems can also provide insight.
- Other production information includes sound controls, scene identifiers, source identifiers, and so on.
- the production information is processed and filtered to produce a collection of symbolic representations of the production information, each symbol corresponding to a determined event or characteristic.
- This symbolic production information is preferably combined with other sources of indexing and summarizing information, to provide a set of annotations to the content material that facilitate efficient and effective selective retrieval.
- the techniques presented herein are also particularly well suited for annotating the content material of videoconferences, to facilitate identification of key segments of a videoconference recording.
- FIG. 1 illustrates an example production scene for gathering audio/video information.
- FIG. 2 illustrates an example block diagram of a production recording system in accordance with this invention.
- FIG. 3 illustrates an example block diagram of an indexing/summarizing system in accordance with this invention.
- FIG. 4 illustrates an example block diagram of a production recorder in accordance with this invention.
- indexing and “summarizing” are used herein to reference particular applications for this invention.
- This invention addresses a method and device for providing information that is associated with content material, and is not limited by how that information is used. Although this provided information may be particularly well suited for use as an index to facilitate a search for material, or for use as a synopsis to facilitate a quick review or preview of the material, one of ordinary skill in the art will recognize that this invention is not limited to these particular applications.
- FIG. 1 illustrates an example production scene for gathering audio/video information.
- the scene includes a director 110 who directs the action of the camera operators 120, 121, as well as the performers 130, 131 and objects 140.
- the example scene is representative of a directed scene.
- this invention is also applicable to an undirected scene, such as the recording of a news or sports event.
- a production director continuously determines which camera is the "on-line” camera, depending upon the current action, directs "off-line” cameras to capture specific scenes for potential selection as the "on-line” camera, or potential use for "instant replay".
- the production director also performs a similar selection of source material for transmission.
- the published scripts, synopses, and scene edit lists, cited above with regard to MPEG-7, may contain appropriately descriptive information, but the published information may not reflect the events as they actually happen on the production site.
- the three example sentences, above convey the information that Joe and Jim are in the scene, that this is the scene wherein briefcases are switched, and so on.
- This production information also conveys information that can be used in an indirect manner to facilitate an interpretation of other sources of information. For example, an image processing system will likely identify this scene as a "group" scene, and may or may not identify Joe or Jim in the group, whereas the example sentences imply that the crowd is merely "background".
- the presence of the automobiles 140 in the scene can also be interpreted as insignificant background information, based on the absence of a reference to them in the production directives. That is, the production information not only conveys direct information regarding the content of the subsequent images, but also provides cues that facilitate efficient processing by other sources of indexing or summarizing information.
- FIG. 2 illustrates an example block diagram of a production recording system 200 in accordance with this invention.
- a production recorder 210 receives information from a variety of sources 220, 230, 240, and produces a database of production information 215 that captures the production information in an efficient form for subsequent processing.
- a primary source of production information is vocal input 220.
- a variety of vocal sources 220 typically provide production information. For example, in a news broadcast, the production booth provides a source of vocal information; the on-site reporter may give directions to an on-site camera operator; before the on-air transmission, the news coordinator may give advice to the studio newscasters, or the on-site reporter, and so on.
- the production recorder 210 is configured to process each of these sources of information, to extract pertinent information, and to record the pertinent information for subsequent use in a retrieval process. Depending upon the complexity of the analysis, this processing may be performed in real time, as the images are being recorded, or as a post-processing task. In a preferred embodiment, the production recorder 210 also directly records the information from the sources 220-240, to facilitate a subsequent selectable degree of processing and analysis.
- the real-time analysis of the production information for example, uses the 'primary' source of production information, such as the vocal information from a microphone associated with the director, and the other sources of production information are processed as required at a later time, for a more detailed analysis and assessment.
- a production recording system 200 in a preferred embodiment includes input 230 corresponding to parameters associated with the individual cameras.
- the zoom setting of a camera can be used to provide a characterization of a scene.
- a narrow-angle, high-zoom setting typically implies a directed focus to an individual or event; or, a change of zoom setting indicates a change of emphasis on the individual or event.
- a wide-angle, or low-zoom setting is typically associated with a "background" or "mood-setting" scene.
- the identification of a series of images being captured at a low zoom setting can be used, for example, by an image-based categorizing system to "skip ahead" to higher zoom setting images, based on this likely correlation of significance and zoom setting.
- each new scene may be assessed, regardless of zoom setting; if the image processor finds little or no discernible information at a particular zoom setting, it may then activate a 'skip-ahead' function. Assuming a consistency in video capture techniques, particularly within the same production, the decision to 'skip-ahead' can be made more and more quickly, thereby improving the efficiency of the image-based categorizing system.
- the orientation, or rate of change of orientation can also be used to characterize a scene. For example, in sports, the capture of a kick-off, forward-pass, or home-run would likely involve a relatively rapid change of camera orientation, whereas an end-line-rush or strike-out would likely not involve a change of camera orientation.
- sources 240 of production information such as the location of sound booms during recording, and other means of identifying the 'focus' of the scene can also be used to facilitate an indexing or summarizing of recorded content material.
- the 'source' of the content material can convey information regarding the scene. For example, in a news broadcast, the identification of a scene as coming from "file footage" can be used to either minimize the processing of the scene, or provide a link to a prior processing and characterizing of this footage. Note that as production tasks become more and more automated, or at least managed via computer resources, the source of production information becomes substantial. For example, a sequencing and selection of sources during a newscast can be expected to be controlled via a computer. The capture of this information for each production can substantially increase the effectiveness and efficiency of other content indexing and summarizing tools.
- the resultant automatically generated camera settings provide the camera input 230 to the production recorder 210, discussed above, with or without any other sources of production information.
- copending US patent application “MULTIMODAL VIDEO TARGET ACQUISITION AND RE-DIRECTION SYSTEM AND METHOD”, serial number 09/488,028, filed 1/20/00 for Eric Cohen-Solal and Mi-Suen Lee, Attorney Docket US000015, discloses a technique and device that adjusts a camera's field of view based on gestures and key words, and is incorporated by reference herein.
- copending US patent applications “METHOD AND APPARATUS FOR TRACKING MOVING OBJECTS USING COMBINED VIDEO AND AUDIO INFORMATION IN VIDEO
- CONFERENCING AND OTHER APPLICATIONS discloses a technique and device that adjusts a camera's field of view based on an analysis of the video and audio content of the scene being recorded.
- the resultant camera settings, and the gestures, speech, and movements used to cause these settings, or the analysis of the gestures, speech, or movements may be provided to the production recorder 210 for use in generating the production information database 215.
- the camera settings during a videoconference can similarly be used to facilitate a characterization of a videoconference session.
- Advanced videoconferencing systems are expected to include the automated and semi-automated camera control features discussed above, and even relatively simple systems allow the participants to the videoconference to adjust the camera field of view, either at their site, or at the remote site.
- a camera operator may be provided at a central site of the videoconference, or at the site of a key speaker, and so on.
- a stationary camera position, with perhaps some variations in zoom, for an extended time duration could be indicative of a keynote address, particularly when correlated to the audio content from each videoconference site.
- a continuing back and forth rotation of the camera could be indicative of a key discussion period.
- this combination of this production information with an analysis of the content material can provide insights that may not be readily apparent from the content material, and thereby improve the quality and efficiency of providing summaries for each videoconference. For example, once the camera setting corresponding to each of a plurality of speakers is determined (or explicitly provided), character identification in images becomes significantly simpler if the camera setting corresponding to the images is used to pre-filter the choices of characters that are provided to the character identification process. Similarly, the speaker identification process can be similarly enhanced by providing camera settings corresponding to each audio track. In like manner, a rapid determination that the audio track does not match the identified participant in the field of view corresponding to the current camera settings can be used to modify the current camera settings to search for the current speaker.
- a time reference 201 is associated with the recorded production information 215.
- some of the production information such as the camera settings 240, will be coincident in time with the scenes of the content material, while other information, such as vocal directives 220 typically precede the scenes to which they apply.
- Knowledge based and heuristic techniques are used to determine a correlation between specific directives 220 and the content material. For example, a directive 220 that is followed with a significant adjustment of camera settings 230, or the occurrence of a 'cut' in scenes, is likely to contain information relevant to the following clip.
- scene identification and synchronizing input 202 may also be provided, particularly in directed scenes, wherein an explicit identification of the scene (e.g. "Rocky IX, Scene 32, Take 3") is available.
- FIG. 3 illustrates an example block diagram of an indexing/summarizing system 300 in accordance with this invention.
- an indexer/summarizer 310 preferably has access to a variety of information 215, 320-323 that facilitates the characterization, or indexing, or summarizing, of content information.
- Closed- caption information 320 is commonly used to characterize content material, such as in the BNE and BNN systems, discussed above.
- the production information can be used to improve the efficiency or effectiveness of this categorizing process.
- the scene of FIG. 1 may include dialog that is included in the closed- caption material, but this dialog may merely be provided as either a diversion from the exchange of briefcases, or merely as filler material while the exchange takes place.
- the indexer/summarizer 310 in a preferred embodiment uses the production information 215 associated with the scene of FIG. 1, for example, to decrease a significance-weighting-factor associated with the closed-caption information 320, while increasing a corresponding significance- weighting-factor associated with the image information 321.
- the image information 321 in the content material is used to categorize content material based on the visual characteristics of each image.
- the scene of FIG. 1 might be characterized as "outdoor, group, vehicles, pedestrians", based on simple pattern and context recognition techniques.
- the indexer/summarizer 310 may also include a recognition of one or more of the actors and actresses in the scene.
- the object tracking facilitates the synchronization of the directives to the content material, by associating the directive sentences to the current or next scene, depending upon whether "Joe” and "Jim” are in the respective scenes.
- Context information 322 also facilitates the characterization of the content material that is provided by the indexer/summarizer 310. For example, if the context of a scene is a sports event, the interpretation of the terminology contained in the production information 215 or closed-caption information 320 may be modified; the correlation between the closed-caption information 320 and the image information 321 is modified, based on the likelihood that the closed-caption information corresponds to the broadcaster, and not necessarily to the individuals portrayed in the images; and so on.
- indexer/summarizer 310 is at a user's home, or is customized for a particular user, user information 323 may also be used to facilitate the characterization of the content material.
- knowledge of the user's preferences and/or habits facilitates the processing of the production information 215, and other information 320-322, by providing a prioritization for particular aspects of the indexer/summarizer 310. For example, if the user rarely retrieves information based on a performer's name, the indexer/summarizer will devote fewer resources to characterizing or indexing the content information based on recognition of characters via the production information 215, and other information 320-322. Conversely, if the user commonly searches for particular performers, the indexer/summarizer 310 spends additional time and resources to track each performer, using the plurality of information sources 215, 320-322, to provide a comprehensive index of the performers who appear in each scene or clip.
- the indexer/summarizer 310 provides information that is appended to the content matter, typically as an annotated version of the content material 350.
- a DVD provider for example, will use the system 300 to provide a DVD that includes the indexing or summarizing information associated with each scene of the content material on the DVD.
- a corresponding DVD player is configured to facilitate a search for particular scenes in the content material based on the included indexing or summarizing information.
- the indexing/summarizing system 300 may be independent of the provider of the content material, and may provide the indexing or summarizing information as an independent adjunct to the content material.
- a vendor may provide this indexing and summarizing information on an Internet site, and may provide an application program that allows a user to effect the aforementioned search via an Internet-access device, such as a Web-TV device, or a personal computer (PC).
- an Internet-access device such as a Web-TV device, or a personal computer (PC).
- FIG. 4 illustrates an example block diagram of a production recorder 210 in accordance with this invention.
- the production recorder 210 includes a speech recognizer 420, a field of view processor 430, and a scene synchronizer 410, for processing the production-related inputs 201-240 from a variety of sources.
- the speech recognizer 420 provides a translation from spoken sounds to recognized words, and is used to process the vocal inputs 220.
- the field of view processor 430 provides an interpretation of camera settings to characterize the current field of view of each camera 230.
- the scene synchronizer 410 processes the synchronizing inputs 201, 202 to facilitate synchronization between the production information and the content material.
- Other processors 440 are provided as required for processing the input from the other sources 240 of production information.
- a symbolic encoder 450 encodes the production information 215 in symbolic form, to facilitate subsequent processing by the indexer/summarizer 310 (FIG. 3).
- the production recorder 210 includes a symbol library 460 that facilitates this symbolic encoding.
- the symbol library 460 in a preferred embodiment includes symbols for key words that the symbolic encoder 450 uses to encode words that are provided by the speech recognizer 420.
- the symbol library includes symbols corresponding to particular camera settings or combinations of settings, to facilitate the encoding of the camera characteristics provided by the field of view processor 420.
- a variety of techniques may be used for maintaining an effective symbol library 460. Copending U.S.
- the production information 215 that is included in the annotated audio/video content 350 may be of direct interest to the user, and may provide a marketing advantage for media that contains this information.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Television Signal Processing For Recording (AREA)
- Management Or Editing Of Information On Record Carriers (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP01978317A EP1393568A2 (en) | 2000-09-11 | 2001-08-27 | System to index/summarize audio/video content |
KR1020027006025A KR20020060964A (en) | 2000-09-11 | 2001-08-27 | System to index/summarize audio/video content |
JP2002526124A JP2004508776A (en) | 2000-09-11 | 2001-08-27 | System for indexing / summarizing audio / image content |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US65918200A | 2000-09-11 | 2000-09-11 | |
US09/659,182 | 2000-09-11 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2002021843A2 true WO2002021843A2 (en) | 2002-03-14 |
WO2002021843A3 WO2002021843A3 (en) | 2003-12-18 |
Family
ID=24644380
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2001/009974 WO2002021843A2 (en) | 2000-09-11 | 2001-08-27 | System to index/summarize audio/video content |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP1393568A2 (en) |
JP (1) | JP2004508776A (en) |
KR (1) | KR20020060964A (en) |
WO (1) | WO2002021843A2 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2004021221A2 (en) * | 2002-08-30 | 2004-03-11 | Hewlett-Packard Development Company, L.P. | System and method for indexing a video sequence |
EP1684198A3 (en) * | 2005-01-20 | 2006-08-09 | Samsung Electronics Co., Ltd. | Digital photo managing apparatus and method, and computer recording medium storing program for executing the method |
US20080052104A1 (en) * | 2005-07-01 | 2008-02-28 | Searete Llc | Group content substitution in media works |
US20080086380A1 (en) * | 2005-07-01 | 2008-04-10 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Alteration of promotional content in media works |
WO2008141539A1 (en) * | 2007-05-17 | 2008-11-27 | Huawei Technologies Co., Ltd. | A caption display method and a video communication system, apparatus |
CN102289490A (en) * | 2011-08-11 | 2011-12-21 | 杭州华三通信技术有限公司 | Video summary generating method and equipment |
CN105096668A (en) * | 2014-05-16 | 2015-11-25 | 北京天宇各路宝智能科技有限公司 | Teaching voice and video manufacturing system and manufacturing method |
US9583141B2 (en) | 2005-07-01 | 2017-02-28 | Invention Science Fund I, Llc | Implementing audio substitution options in media works |
Citations (3)
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 |
WO1998057251A1 (en) * | 1997-06-13 | 1998-12-17 | Panavision, Inc. | Multiple camera video assist control system |
WO1999036863A2 (en) * | 1998-01-13 | 1999-07-22 | Koninklijke Philips Electronics N.V. | System and method for selective retrieval of a video sequence |
-
2001
- 2001-08-27 KR KR1020027006025A patent/KR20020060964A/en not_active Application Discontinuation
- 2001-08-27 JP JP2002526124A patent/JP2004508776A/en active Pending
- 2001-08-27 WO PCT/EP2001/009974 patent/WO2002021843A2/en not_active Application Discontinuation
- 2001-08-27 EP EP01978317A patent/EP1393568A2/en not_active Withdrawn
Patent Citations (3)
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 |
WO1998057251A1 (en) * | 1997-06-13 | 1998-12-17 | Panavision, Inc. | Multiple camera video assist control system |
WO1999036863A2 (en) * | 1998-01-13 | 1999-07-22 | Koninklijke Philips Electronics N.V. | System and method for selective retrieval of a video sequence |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2004021221A2 (en) * | 2002-08-30 | 2004-03-11 | Hewlett-Packard Development Company, L.P. | System and method for indexing a video sequence |
WO2004021221A3 (en) * | 2002-08-30 | 2004-07-15 | Hewlett Packard Development Co | System and method for indexing a video sequence |
US7483624B2 (en) | 2002-08-30 | 2009-01-27 | Hewlett-Packard Development Company, L.P. | System and method for indexing a video sequence |
EP1684198A3 (en) * | 2005-01-20 | 2006-08-09 | Samsung Electronics Co., Ltd. | Digital photo managing apparatus and method, and computer recording medium storing program for executing the method |
US20080052104A1 (en) * | 2005-07-01 | 2008-02-28 | Searete Llc | Group content substitution in media works |
US20080086380A1 (en) * | 2005-07-01 | 2008-04-10 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Alteration of promotional content in media works |
US9583141B2 (en) | 2005-07-01 | 2017-02-28 | Invention Science Fund I, Llc | Implementing audio substitution options in media works |
WO2008141539A1 (en) * | 2007-05-17 | 2008-11-27 | Huawei Technologies Co., Ltd. | A caption display method and a video communication system, apparatus |
CN102289490A (en) * | 2011-08-11 | 2011-12-21 | 杭州华三通信技术有限公司 | Video summary generating method and equipment |
CN105096668A (en) * | 2014-05-16 | 2015-11-25 | 北京天宇各路宝智能科技有限公司 | Teaching voice and video manufacturing system and manufacturing method |
Also Published As
Publication number | Publication date |
---|---|
JP2004508776A (en) | 2004-03-18 |
EP1393568A2 (en) | 2004-03-03 |
WO2002021843A3 (en) | 2003-12-18 |
KR20020060964A (en) | 2002-07-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR100711948B1 (en) | Personalized video classification and retrieval system | |
Dimitrova et al. | Applications of video-content analysis and retrieval | |
Hanjalic | Content-based analysis of digital video | |
US8528019B1 (en) | Method and apparatus for audio/data/visual information | |
CA2924065C (en) | Content based video content segmentation | |
US7143353B2 (en) | Streaming video bookmarks | |
EP1692629B1 (en) | System & method for integrative analysis of intrinsic and extrinsic audio-visual data | |
US7181757B1 (en) | Video summary description scheme and method and system of video summary description data generation for efficient overview and browsing | |
US20050028194A1 (en) | Personalized news retrieval system | |
US20030234803A1 (en) | System and method for automatically generating video cliplets from digital video | |
WO2007004110A2 (en) | System and method for the alignment of intrinsic and extrinsic audio-visual information | |
Chen et al. | Detection of soccer goal shots using joint multimedia features and classification rules | |
Gauch et al. | Real time video scene detection and classification | |
KR20030023576A (en) | Image information summary apparatus, image information summary method and image information summary processing program | |
US8051446B1 (en) | Method of creating a semantic video summary using information from secondary sources | |
EP1393568A2 (en) | System to index/summarize audio/video content | |
Wang et al. | Automatic composition of broadcast sports video | |
KR20220005255A (en) | Apparatus for Learning Recognition Model, Apparatus for Analyzing Video and Apparatus for Providing Video Searching Service | |
Chen et al. | Multi-criteria video segmentation for TV news | |
Volkmer et al. | Gradual transition detection using average frame similarity | |
Zhu et al. | Automatic scene detection in news program by integrating visual feature and rules | |
Hu et al. | Combined-media video tracking for summarization | |
Papachristou et al. | Human-centered 2D/3D video content analysis and description | |
Aas et al. | A survey on: Content-based access to image and video databases | |
Dimitrova et al. | Selective video content analysis and filtering |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): JP KR |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
ENP | Entry into the national phase |
Ref country code: JP Ref document number: 2002 526124 Kind code of ref document: A Format of ref document f/p: F |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020027006025 Country of ref document: KR |
|
WWP | Wipo information: published in national office |
Ref document number: 1020027006025 Country of ref document: KR |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2001978317 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2003107921 Country of ref document: RU Kind code of ref document: A Format of ref document f/p: F |
|
WWP | Wipo information: published in national office |
Ref document number: 2001978317 Country of ref document: EP |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: 2001978317 Country of ref document: EP |