Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based 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.
@article{arxiv.1711.07430,
title = {Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion},
author = {Weiyao Lin and Yang Mi and Jianxin Wu and Ke Lu and Hongkai Xiong},
journal= {arXiv preprint arXiv:1711.07430},
year = {2017}
}