Multi-region two-stream R-CNN for action detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

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


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.
Fichier principal
Vignette du fichier
eccv16-pxj-v3.pdf (4.5 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01349107 , version 1 (26-07-2016)
hal-01349107 , version 2 (04-12-2016)
hal-01349107 , version 3 (05-01-2017)



Xiaojiang Peng, Cordelia Schmid. Multi-region two-stream R-CNN for action detection. ECCV - European Conference on Computer Vision, Oct 2016, Amsterdam, Netherlands. pp.744-759, ⟨10.1007/978-3-319-46493-0_45⟩. ⟨hal-01349107v3⟩
6021 View
5842 Download



Gmail Facebook X LinkedIn More