Scene Extraction for Video Clips Based on the Relation of Text, Pointing Region and Temporal Duration of User Comments

Recently, video sharing websites that allow users to attach comments to video clips have attracted much attention. In this paper, we propose a method whereby users can easily retrieve video scenes relevant to their interest. Our system makes both a text and non-text analysis of a user's comment and then retrieves and displays relevant scenes for viewing of the scenes along with attached comments. The text analysis works in tandem with non-text features, namely, the pointing region and temporal duration of user comments. In this way, our system supports a better organized retrieval of scenes that have attached user comments with a higher degree of relevancy for the user than is currently available with conventional methods, for example, using matching keywords. We describe here our method and the relation between the scenes and discuss a prototype system.

[1]  T. Kimura,et al.  A video editing support system using users' gazes , 2005, PACRIM. 2005 IEEE Pacific Rim Conference on Communications, Computers and signal Processing, 2005..

[2]  Yihong Gong.  An accurate and robust method for detecting video shot boundaries , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[3]  Atsuo Yoshitaka,et al.  Scene detection by audio-visual features , 2001, IEEE International Conference on Multimedia and Expo, 2001. ICME 2001..

[4]  Keishi Tajima,et al.  A query model for retrieving relevant intervals within a video stream , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[5]  Kenichi Yoshida,et al.  Annotating TV drama based on viewer dialogue - analysis of viewers' attention generated on an Internet bulletin board , 2005, The 2005 Symposium on Applications and the Internet.

[6]  K. Nagao,et al.  Weblog-style video annotation and syndication , 2005, First International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution (AXMEDIS'05).

[7]  Katsumi Tanaka,et al.  Generating Football Video Summery Using News Article , 2003 .

[8]  Kazutoshi Sumiya,et al.  Organizing User Comments in a Social Video Sharing System by Temporal Duration and Pointing Region , 2008, 2008 International Workshop on Information-Explosion and Next Generation Search.

[9]  Noboru Babaguchi,et al.  Sports event detection using temporal patterns mining and web-casting text , 2008, AREA '08.

[10]  Yen-Liang Chen,et al.  Mining Nonambiguous Temporal Patterns for Interval-Based Events , 2007, IEEE Transactions on Knowledge and Data Engineering.

[11]  Katashi Nagao,et al.  Video Scene Retrieval Using Online Video Annotation , 2007, JSAI.

[12]  C. Saraceno,et al.  Identification of successive correlated camera shots using audio and video information , 1997, Proceedings of International Conference on Image Processing.

[13]  Satoshi Nakamura,et al.  Generation of views of TV content using TV viewers' perspectives expressed in live chats on the web , 2005, MULTIMEDIA '05.

[14]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[15]  Nobuyuki Yagi,et al.  Automatic Generation of a Multimedia Encyclopedia from TV Programs by Using Closed Captions and Detecting Principal Video Objects , 2006, Eighth IEEE International Symposium on Multimedia (ISM'06).