Abstract
In this paper, we consider two action recognition problems in still images. One is the conventional action classi?cation task where we assign a class label to each action image; the other is a new problem where we measure the similarity between action images. We achieve the goals by using a mutual context model to jointly model the objects and human poses in images of human actions. Experimental results show that our method not only improves action classi?cation accuracy, but also learns a similarity measure that is largely consistent with human perception.