ML Anthology

Successive Convex Matching for Action Detection

Hao Jiang, Mark S. Drew, Ze-Nian Li
CVPR 2006 pp. 1646-1653
doi:10.1109/CVPR.2006.297 /cvpr/2006/jiang2006cvpr-successive/

Abstract

We propose human action detection based on a successive convex matching scheme. Human actions are represented as sequences of postures and specific actions are detected in video by matching the time-coupled posture sequences to video frames. The template sequence to video registration is formulated as an optimal matching problem. Instead of directly solving the highly non-convex problem, our method convexifies the matching problem into linear programs and refines the matching result by successively shrinking the trust region. The proposed scheme represents the target point space with small sets of basis points and therefore allows efficient searching. This matching scheme is applied to robustly matching a sequence of coupled binary templates simultaneously in a video sequence with cluttered backgrounds.

CVPR Semantic Scholar

Cite

Text

Jiang et al. "Successive Convex Matching for Action Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.297

Markdown

[Jiang et al. "Successive Convex Matching for Action Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/jiang2006cvpr-successive/) doi:10.1109/CVPR.2006.297

BibTeX

@inproceedings{jiang2006cvpr-successive,
  title     = {{Successive Convex Matching for Action Detection}},
  author    = {Jiang, Hao and Drew, Mark S. and Li, Ze-Nian},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {1646-1653},
  doi       = {10.1109/CVPR.2006.297},
  url       = {https://mlanthology.org/cvpr/2006/jiang2006cvpr-successive/}
}