Joint spatial-temporal attention for action recognition

In this paper, we propose a novel high-level action representation using joint spatial-temporal attention model, with application to video-based human action recognition. Specifically, to extract robust motion representations of videos, a new spatial attention module based on 3D convolution is proposed, which can pay attention to the salient parts of the spatial areas. For better dealing with long-duration videos, a new bidirectional LSTM based temporal attention module is introduced, which aims to focus on the key video cubes instead of the key video frames of a given video. The spatial-temporal attention network can be jointly trained via a two-stage strategy, which enables us to simultaneously explore the correlation both in spatial and temporal domain. Experimental results on benchmark action recognition datasets demonstrate the effectiveness of our network. (c) 2018 Elsevier B.V. All rights reserved.