Disclosure of Non-scripted Video Content: InDiCo and M4/AMI

The paper discusses three IST projects focusing on the disclosure of video content via a combination of low-level multimodal feature analysis, content abstraction, and browsing tools. The type of content (recordings of conference lectures and meetings) can be characterized as non-scripted and is argued to generate a whole range of new research issues. Performance results are reported for some of the tools developed in InDiCo and M4

[1]  Iain McCowan,et al.  Clustering and segmenting speakers and their locations in meetings , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Paul Over,et al.  TRECVID: evaluating the effectiveness of information retrieval tasks on digital video , 2004, MULTIMEDIA '04.

[3]  John R. Smith,et al.  Intelligent multimedia information retrieval , 1997 .

[4]  Andreas Stolcke,et al.  The Meeting Project at ICSI , 2001, HLT.

[5]  de Franciska Jong,et al.  OLIVE: Speech-Based Video Retrieval , 1998 .

[6]  Walter Daelemans,et al.  TiMBL: Tilburg Memory-Based Learner, version 2.0, Reference guide , 1998 .

[7]  Daniel P. W. Ellis,et al.  Audio information access from meeting rooms , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[8]  de Jong,et al.  Human language as Elsnet Interlingua: Intelligent multimedia indexing , 1998 .

[9]  Djoerd Hiemstra,et al.  Language-Based Multimedia Information Retrieval , 2000, RIAO.