Multi-region two-stream R-CNN for action detection

Xiaojiang Peng (1) , Cordelia Schmid (1)

1 Thoth - Apprentissage de modèles à partir de données massives

We propose a multi-region two-stream R-CNN model for action detection in realistic videos. We start from frame-level action detection based on faster R-CNN [1], and make three contributions: (1) we show that a motion region proposal network generates high-quality proposals , which are complementary to those of an appearance region proposal network; (2) we show that stacking optical flow over several frames significantly improves frame-level action detection; and (3) we embed a multi-region scheme in the faster R-CNN model, which adds complementary information on body parts. We then link frame-level detections with the Viterbi algorithm, and temporally localize an action with the maximum subarray method. Experimental results on the UCF-Sports, J-HMDB and UCF101 action detection datasets show that our approach outperforms the state of the art with a significant margin in both frame-mAP and video-mAP.

Keywords: Action detection; faster R-CNN; multi-region CNNs; two stream R-CNN

Domains: Computer Vision and Pattern Recognition [cs.CV]

Xiaojiang Peng, Cordelia Schmid. Multi-region two-stream R-CNN for action detection. ECCV 2016 - European Conference on Computer Vision, Oct 2016, Amsterdam, Netherlands. ⟨hal-01349107v2⟩