Action Recognition With Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion

Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deepbased framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams. We first introduce a coarse-to-fine network which extracts shared deep features at different action class granularities and progressively integrates them to obtain a more accurate feature representation for input actions. We further introduce an asynchronous fusion network. It fuses information from different streams by asynchronously integrating stream-wise features at different time points, hence better leveraging the complementary information in different streams. Experimental results on action recognition benchmarks demonstrate that our approach achieves the state-of-the-art performance.

Authors

• Weiyao Lin Shanghai Jiao Tong university
• Chongyang Zhang Shanghai Jiao Tong University, Shanghai, China
• Ke Lu University of Electronic Science and Technology of China
• Bin Sheng Shanghai Jiao Tong University
• Jianxin Wu National Key Laboratory for Novel Software Technology, Nanjing University, China School of Artificial Intelligence, Nanjing University, China
• Bingbing Ni Shanghai Jiao Tong University
• Xin Liu
• Hongkai Xiong Shanghai Jiao Tong University

Keywords

No keywords are indexed for this paper.