Recognizing actions from still images

Creative Commons License

Ikizler N., CİNBİŞ R. G., Pehlivan Tort S., DUYGULU ŞAHİN P.

Proceedings - International Conference on Pattern Recognition, 2008 (Scopus) identifier


In this paper, we approach the problem of under- standing human actions from still images. Our method involves representing the pose with a spatial and ori- entational histogramming of rectangular regions on a parse probability map. We use LDA to obtain a more compact and discriminative feature representation and binary SVMs for classification. Our results over a new dataset collected for this problem show that by using a rectangle histogramming approach, we can discriminate actions to a great extent. We also show how we can use this approach in an unsupervised setting. To our best knowledge, this is one of the first studies that try to recognize actions within still images. © 2008 IEEE.