Action recognition from weak alignment of body parts

We propose a method for human action recognition from still images that uses the silhouette and the upper body as a proxy for the pose of the person, and also to guide alignment between instances for the purpose of computing registered feature descriptors. Our contributions include an efficient algorithm, formulated as an energy minimization, for using the silhouette to align body parts between imaged human samples. The descriptors computed over the aligned body parts are incorporated in a multiple kernel framework to learn a classifier for each action class. Experiments on the challenging PASCAL VOC 2012 dataset show that our method outperforms the state-of-the-art on the majority of action classes.