Abstract
In this paper, we address the problem of action recognition from still images and videos. Traditional local features such as SIFT and STIP invariably pose two potential problems: 1) they are not evenly distributed in different entities of a given category and 2) many of such features are not exclusive of the visual concept the entities represent. In order to generate a dictionary taking the aforementioned issues into account, we propose a novel discriminative method for identifying robust and category specific local features which maximize the class separability to a greater extent. Specifically, we pose the selection of potent local descriptors as filtering-based feature selection problem, which ranks the local features per category based on a novel measure of distinctiveness. The underlying visual entities are subsequently represented based on the learned dictionary, and this stage is followed by action classification using the random forest model followed by label propagation refinement. The framework is validated on the action recognition datasets based on still images (Stanford-40) as well as videos (UCF-50). We get 51.2% and 66.7% recognition accuracy for Standford-40 and UCF-50, respectively. Compared to other representative methods from the literature, our approach exhibits superior performances. This proves the effectiveness of adaptive ranking methodology presented in this work.