Search video action proposal with recurrent and static YOLO

Romain Vial, Hongyuan Zhu, Yonghong Tian, Shijian Lu

Abstract

In this paper, we propose a new approach for searching action proposals in unconstrained videos. Our method first produces snippet action proposals by combining state-of-the-art YOLO detector (Static YOLO) and our regression based RNN detector (Recurrent YOLO). Then, these short action proposals are integrated to form final action proposals by solving two-pass dynamic programming which maximizes actioness score and temporal smoothness concurrently. Our experimental comparison with other state-of-the-arts on challenging UCF101 dataset shows that our method advances state-of-the-art proposal generation performance while maintaining low computational cost.
BibTeX
@inproceedings{vial2017search,
  author = {Romain Vial and Hongyuan Zhu and Yonghong Tian and Shijian Lu},
  title = {{Search video action proposal with recurrent and static YOLO}},
  booktitle = {ICIP},
  year = {2017},
  doi = {10.1109/icip.2017.8296639},
}

Loading related content...

Figure