ML Anthology

Dynamic Bayesian Framework for Extracting Temporal Structure in Video

Ankush Mittal, Loong Fah Cheong, Leung Tung Sing
CVPR 2001 pp. II:110-115
doi:10.1109/CVPR.2001.990933 /cvpr/2001/mittal2001cvpr-dynamic/

Abstract

In this paper, we develop the concept of descriptors based on perceptual-level motion features such as time-to-collision, shot transition and temporal motion and it is shown that by including them the representational level of the video classes is significantly enhanced, e.g. violence could be detected. The temporal context cues, which had been largely neglected by present content-based retrieval (CBR) systems, are integrated into the framework. A dynamic Bayesian framework for the CBR systems which can learn the temporal structure through the fusion of all the features is designed The experimental results for more than 4 hours of videos are presented for a number of key applications like sequence identifier, highlight extraction for sports, and detecting climax or violence.

CVPR Semantic Scholar

Cite

Text

Mittal et al. "Dynamic Bayesian Framework for Extracting Temporal Structure in Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990933

Markdown

[Mittal et al. "Dynamic Bayesian Framework for Extracting Temporal Structure in Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/mittal2001cvpr-dynamic/) doi:10.1109/CVPR.2001.990933

BibTeX

@inproceedings{mittal2001cvpr-dynamic,
  title     = {{Dynamic Bayesian Framework for Extracting Temporal Structure in Video}},
  author    = {Mittal, Ankush and Cheong, Loong Fah and Sing, Leung Tung},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:110-115},
  doi       = {10.1109/CVPR.2001.990933},
  url       = {https://mlanthology.org/cvpr/2001/mittal2001cvpr-dynamic/}
}