2004
A dynamic probabilistic retrieval model
Publication
Publication
Presented at the
IEEE International Conference on Multimedia and Expo, Taipei, Taiwan
We describe the application of a probabilistic multimedia model to video retrieval. From video shots, we compute Gaussian-mixture models that capture correlations in time and space, such as the appearance and disappearance of objects. These models improve the precision of "query by example/s" results in the TRECVID 2003 collection when compared to models that only make use of static visual information. Furthermore, integrated with information from automatic speech recognition (ASR) transcripts, they outperform ASR only results
| Additional Metadata | |
|---|---|
| IEEE | |
| IEEE International Conference on Multimedia and Expo | |
| Organisation | Database Architectures |
|
Ianeva, T., de Vries, A., & Westerveld, T. (2004). A dynamic probabilistic retrieval model. In Proceedings of IEEE International Conference on Multimedia and Expo 2004 (ICME) (pp. 1–4). IEEE. |
|
