Recognizing Realistic Actions from Videos in the Wild

In this paper, we present a systematic framework for re-cognizing realistic actions from videos “in the wild.” Such unconstrained videos are abundant in personal collections as well as on the web. Recognizing action from such videos has not been addressed extensively, primarily due to the tremendous variations that result from camera motion, background clutter, changes in object appearance, and scale, etc. The main challenge is how to extract reliable and informative features from the unconstrained videos. We extract both motion and static features from the videos. Since the raw features of both types are dense yet noisy, we propose strategies to prune these features. We use motion statistics to acquire stable motion features and clean static features. Furthermore, PageRank is used to mine the most informative static features. In order to further construct compact yet discriminative visual vocabularies, a divisive information-theoretic algorithm is employed to group se-mantically r...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Jingen Liu (University of Central Florida), Jiebo Luo (Kodak Research Labs), Mubarak Shah (University of Central Florida)
• Keywords: AdaBoost, Computer Vision, CVPR 2009, KTH Dataset, Object Recognition, Realistic Actions, Video Analysis