Spatio-temporal Shape and Flow Correlation for Action Recognition

This paper explores the use of volumetric features for action recognition. First, we propose a novel method to correlate spatio-temporal shapes to video clips that have been automatically segmented. Our method works on oversegmented videos, which means that we do not require background subtraction for reliable object segmentation. Next, we discuss and demonstrate the complementary nature of shape- and flow-based features for action recognition. Our method, when combined with a recent flow-based correlation technique, can detect a wide range of actions in video, as demonstrated by results on a long tennis video. Although not specifically designed for whole-video classification, we also show that our method's performance is competitive with current action classification techniques on a standard video classification dataset.

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Yan Ke, Rahul Sukthankar, Martial Hebert
• Keywords: Action Classification Techniques, Action Recognition, Computer Vision, CVPR 2007, Long Tennis Video, Reliable Object Segmentation, Video Classification Dataset