Human Action Recognition With Trajectory Based Covariance Descriptor In Unconstrained Videos

Human action recognition from realistic videos plays a key role in multimedia event detection and understanding. In this paper, a novel Trajectory Based Covariance (TBC) descriptor is proposed, which is formulated along the dense trajectories. To map the descriptor matrix to vector space and trim out the redundancy of data, the TBC descriptor matrix is projected to Euclidean space by the Logarithm Principal Components Analysis (LogPCA). Our method is tested on the challenging Hollywood2 and TV Human Interaction datasets. Experimental results show that the proposed TBC descriptor outperforms three baseline descriptors (i.e., histogram of oriented gradient, histogram of optical flow and motion boundary histogram), and our method achieves better recognition performances than a number of state-of-the-art approaches. Categories and Subject Descriptors I.2.10 [Artificial Intelligence]: Vision and Scene Understanding General Terms Algorithms, Experimentation, Performance Keywords TBC Descr...

• Type: Journal
• Year: 2015
• Where: MM
• Authors: Hanli Wang, Yun Yi, Jun Wu
• Keywords: MM 2015, Multimedia