Action Recognition with Actons

Jun Zhu, Baoyuan Wang, Xiaokang Yang, Wenjun Zhang, Zhuowen Tu
2013 2013 IEEE International Conference on Computer Vision  
With the improved accessibility to an exploding amount of video data and growing demands in a wide range of video analysis applications, video-based action recognition/classification becomes an increasingly important task in computer vision. In this paper, we propose a two-layer structure for action recognition to automatically exploit a mid-level "acton" representation. The weakly-supervised actons are learned via a new max-margin multi-channel multiple instance learning framework, which can
more » ... pture multiple mid-level action concepts simultaneously. The learned actons (with no requirement for detailed manual annotations) observe the properties of being compact, informative, discriminative, and easy to scale. The experimental results demonstrate the effectiveness of applying the learned actons in our two-layer structure, and show the state-ofthe-art recognition performance on two challenging action datasets, i.e., Youtube and HMDB51.
doi:10.1109/iccv.2013.442 dblp:conf/iccv/ZhuWYZT13 fatcat:otes2ngysncjldnmsfwfpe7cj4