20th International Conference on Pattern Recognition Conference, İstanbul, Türkiye, 23 - 26 Nisan 2010, cilt.6388, ss.306-312
This paper presents two variations of a Hough-voting frame-work used for action recognition and shows classification results for low-resolution video and videos depicting human interactions. For low-resolution videos, where people performing actions are around 30 pixels, we adopt low-level features such as gradients and optical flow. For group actions with human-human interactions, we take the probabilistic action labels from the Hough-voting framework for single individuals and combine them into group actions using decision profiles and classifier combination.