Action recognition based on overcomplete independent components analysis

Abstract

Existing works on action recognition rely on two separate stages: (1) designing hand-designed features or learning features from video data; (2) classifying features using a classifier such as SVM or AdaBoost. Motivated by two observations: (1) independent component analysis (ICA) is capable of encoding intrinsic features underlying video data; and (2) videos of different actions can be easily distinguished by their intrinsic features, we propose a simple but effective action recognition framework based on the recently proposed overcomplete ICA model. After a set of overcomplete ICA basis functions are learned from the densely sampled 3D patches from training videos for each action, a test video is classified as the class whose basis functions can reconstruct the sampled 3D patches from the test video with the smallest reconstruction error. The experimental results on five benchmark datasets demonstrate that the proposed approach outperforms several state-of-the-art works.