Statistical models for automatic video annotation and retrieval

@article{Lavrenko2004StatisticalMF,
  title={Statistical models for automatic video annotation and retrieval},
  author={Victor Lavrenko and Shaolei Feng and R. Manmatha},
  journal={2004 IEEE International Conference on Acoustics, Speech, and Signal Processing},
  year={2004},
  volume={3},
  pages={iii-1044}
}
We apply a continuous relevance model (CRM) to the problem of directly retrieving the visual content of videos using text queries. The model computes a joint probability model for image features and words using a training set of annotated images. The model may then be used to annotate unseen test images. The probabilistic annotations are used for retrieval using text queries. We also propose a modified model - the normalized CRM - which substantially improves performance on a subset of the TREC… CONTINUE READING
Highly Influential
This paper has highly influenced 11 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 95 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 68 extracted citations

96 Citations

01020'06'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 96 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Experimental Evaluation of a Generative Probabilistic Image Retrieval Model on ’Easy

  • T. Westerveld, A. P. de Vries
  • Proceedings of the SI- GIR Multimedia Information…
  • 2003
2 Excerpts

The TREC-2002 video track report

  • A. F. Smeaton, P. Over
  • The Eleventh Text REtrieval Conference
  • 2002
1 Excerpt

Similar Papers

Loading similar papers…