Discriminative Subvolume Search for Efficient Action Detection

Actions are spatio-temporal patterns which can be characterized by collections of spatio-temporal invariant features. Detection of actions is to find the re-occurrences (e.g. through pattern matching) of such spatio-temporal patterns. This paper addresses two critical issues in pattern matching-based action detection: (1) efficiency of pattern search in 3D videos and (2) tolerance of intra-pattern variations of actions. Our contributions are two-fold. First, we propose a discriminative pattern matching called naive- Bayes based mutual information maximization (NBMIM) for multi-class action categorization. It improves the stateof- the-art results on standard KTH dataset. Second, a novel search algorithm is proposed to locate the optimal subvolume in the 3D video space for efficient action detection. Our method is purely data-driven and does not rely on object detection, tracking or background subtraction. It can well handle the intra-pattern variations of actions such as...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Junsong Yuan (Northwestern University), Zicheng Liu (Microsoft Research), Ying Wu (Northwestern University)
• Keywords: Computer Vision, CVPR 2009, Efficient Action Detection, Subvolume Search