Generative Group Activity Analysis with Quaternion Descriptor

Abstract

Activity understanding plays an essential role in video content analysis and remains a challenging open problem. Most of previous research is limited due to the use of excessively localized features without sufficiently encapsulating the interaction context or focus on simply discriminative models but totally ignoring the interaction patterns. In this paper, a new approach is proposed to recognize human group activities. Firstly, we design a new quaternion descriptor to describe the interactive insight of activities regarding the appearance, dynamic, causality and feedback, respectively. The designed descriptor is capable of delineating the individual and pairwise interactions in the activities. Secondly, considering both activity category and interaction variety, we propose an extended pLSA (probabilistic Latent Semantic Analysis) model with two hidden variables. This extended probabilistic graphic paradigm constructed on the quaternion descriptors facilitates the effective inference of activity categories as well as the exploration of activity interaction patterns. The experiments on the realistic movie and human activity databases validate that the proposed approach outperforms the state-of-the-art results.