Our experiments for TRECVID 2004 further investigate the applicability of the so-called “Generative Probabilistic Models to video retrieval��?. TRECVID 2003 results demonstrated that mixture models computed from video shot sequences improve the precision of “query by examples��? results when compared to models computed from keyframes. This year, we extended these video models to capture more complex temporal events, by building generative probabilistic models from the shots using the full covariance matrix instead of a diagonal covariance matrix.
Also, we improved upon the models of the associated textual data (from ASR and OCR) by introducing a multi-layered hierarchical language model. Finally, we tried to take advantage of the information in the audio channel. In the interactive experiments, we experimented with the automatic selection of the media representation (visual, textual or combined) that is most informative for answering the user’s information need.
|Title of host publication||TREC Video Retrieval Evaluation Online Proceedings (TRECVID 2004)|
|Place of Publication||Gaithersburg, MD, USA|
|Publisher||NIST Special Publications|
|Number of pages||10|
|ISBN (Print)||not assigned|
|Publication status||Published - Mar 2005|
|Event||TREC Video Retrieval Evaluation, TRECVID 2004 - Gaithersburg, MD, USA|
Duration: 15 Nov 2004 → 16 Nov 2004
|Name||TREC Video Retrieval Evaluation Online Proceedings|
|Publisher||National Institute of Standards and Technology (NIST)|
|Workshop||TREC Video Retrieval Evaluation, TRECVID 2004|
|Period||15/11/04 → 16/11/04|
|Other||15-16 November 2004|
- DB-MMR: MULTIMEDIA RETRIEVAL