Action detection using multiple spatial-temporal interest point features

This paper considers the problem of detecting actions from clut-tered videos. Compared with the classical action recognition problem, this paper aims to estimate not only the scene category of a given video sequence, but also the spatial-temporal loca-tions of the action instances. In recent years, many feature ex-traction schemes have been designed to describe various aspects of actions. However, due to the difficulty of action detection, e.g., the cluttered background and potential occlusions, a sin-gle type of features cannot solve the action detection problems perfectly in cluttered videos. In this paper, we attack the detec-tion problem by combining multiple Spatial-Temporal Interest Point (STIP) features, which detect salient patches in the video domain, and describe these patches by feature of local regions. The difficulty of combining multiple STIP features for action detection is two folds: First, the number of salient patches de-tected by different STIP methods varies across different salient patches. How to combine such features is not considered by existing fusion methods [13] [5]. Second, the detection in the videos should be efficient, which excludes many slow machine learning algorithms. To handle these two difficulties, we pro-pose a new approach which combines Gaussian Mixture Model with Branch-and-Bound search to efficiently locate the action of interest. We build a new challenging dataset for our action detection task, and our algorithm obtains impressive results. On classical KTH dataset, our method outperforms the state-of-the-art methods. 1