ML Anthology

Progressive Learning for Interactive Surveillance Scenes Retrieval

Jérôme Meessen, Xavier Desurmont, Jean-François Delaigle, Christophe De Vleeschouwer, Benoît Macq
CVPR 2007
doi:10.1109/CVPR.2007.383517 /cvpr/2007/meessen2007cvpr-progressive/

Abstract

This paper tackles the challenge of interactively retrieving visual scenes within surveillance sequences acquired with fixed camera. Contrarily to today's solutions, we assume that no a-priori knowledge is available so that the system must progressively learn the target scenes thanks to interactive labelling of a few frames by the user. The proposed method is based on very low-cost features extraction and integrates relevance feedback, multiple-instance SVM classification and active learning. Each of these 3 steps runs iteratively over the session, and takes advantage of the progressively increasing training set. Repeatable experiments on both simulated and real data demonstrate the efficiency of the approach and show how it allows reaching high retrieval performances.

CVPR Semantic Scholar

Cite

Text

Meessen et al. "Progressive Learning for Interactive Surveillance Scenes Retrieval." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383517

Markdown

[Meessen et al. "Progressive Learning for Interactive Surveillance Scenes Retrieval." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/meessen2007cvpr-progressive/) doi:10.1109/CVPR.2007.383517

BibTeX

@inproceedings{meessen2007cvpr-progressive,
  title     = {{Progressive Learning for Interactive Surveillance Scenes Retrieval}},
  author    = {Meessen, Jérôme and Desurmont, Xavier and Delaigle, Jean-François and De Vleeschouwer, Christophe and Macq, Benoît},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383517},
  url       = {https://mlanthology.org/cvpr/2007/meessen2007cvpr-progressive/}
}