论文信息 - Cluster-temporal browsing of large news video databases

Cluster-temporal browsing of large news video databases

The paper describes cluster-temporal browsing of news video databases. Cluster-temporal browsing combines content similarities and temporal adjacency into a single representation. Visual, conceptual and lexical features are used to organize and view similar shot content. Interactive experiments with eight test users have been carried out using a database of roughly 60 hours of news video. Results indicate improvements in browsing efficiency when automatic speech recognition transcripts are incorporated into browsing by visual similarity. The cluster-temporal browsing application received positive comments from the test users and performed well in overall comparison with interactive video retrieval systems in TRECVID 2003 evaluation.

Timo Ojala | Mika Rautiainen | Tapio Seppänen

[1] Kerry Rodden,et al. How do people manage their digital photographs? , 2003, CHI '03.

[2] Gerard Salton,et al. On the Specification of Term Values in Automatic Indexing , 1973 .

[3] G. G. Stokes. "J." , 1890, The New Yale Book of Quotations.

[4] Jean-Luc Gauvain,et al. The LIMSI Broadcast News transcription system , 2002, Speech Commun..

[5] Mika Rautiainen,et al. Detecting Semantic Concepts from Video Using Temporal Gradients and Audio Classification , 2003, CIVR.

[6] Dragutin Petkovic,et al. Query by Image and Video Content: The QBIC System , 1995, Computer.

[7] Stephen W. Smoliar,et al. An integrated system for content-based video retrieval and browsing , 1997, Pattern Recognit..

[8] Boon-Lock Yeo,et al. Video browsing using clustering and scene transitions on compressed sequences , 1995, Electronic Imaging.

[9] Mika Rautiainen,et al. Temporal color correlograms for video retrieval , 2002, Object recognition supported by user interaction for service robots.

[10] Timo Ojala,et al. TRECVID 2003 Experiments at Media Team Oulu and VTT , 2003, TRECVID.