A Unified Framework for Event Summarization and Rare Event Detection

Abstract

In this paper, we have proposed an unified framework for event summarization and rare event detection and presented the graph-structure learning and editing method to solve these problems efficiently. The experimental results demonstrated that the proposed method outperformed conventional algorithms in complex and crowded public scenes by exploiting and utilizing causality, frequency, and significance of relations of events.

Cite

Text

Kwon and Lee. "A Unified Framework for Event Summarization and Rare Event Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247810

Markdown

[Kwon and Lee. "A Unified Framework for Event Summarization and Rare Event Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/kwon2012cvpr-unified/) doi:10.1109/CVPR.2012.6247810

BibTeX

@inproceedings{kwon2012cvpr-unified,
  title     = {{A Unified Framework for Event Summarization and Rare Event Detection}},
  author    = {Kwon, Junseok and Lee, Kyoung Mu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {1266-1273},
  doi       = {10.1109/CVPR.2012.6247810},
  url       = {https://mlanthology.org/cvpr/2012/kwon2012cvpr-unified/}
}