期刊论文

Qin, Qianqing

英文

Pattern Recognition

0031-3203

2018

79

1

32-43

10.1016/j.patcog.2018.01.020

This work is supported by the Singapore Ministry of Education Academic Research Fund Tier 2 MOE2015-T2-2-114 , and by grants from Office of Naval Research, US. Any opinions expressed in this material are those of the authors and do not necessarily reflect the views of ONR. It was also supported by the Natural Science Foundation of China ( 61501198 ), Natural Science Foundation of Hubei Province ( 2014CFB461 ), Wuhan Youth Science and Technology Chenguang program (2014072704011248), the Dutch national program COMMIT and Dutch NWO TOP grant ARBITER.

本校为其他机构

The most successful video-based human action recognition methods rely on feature representations extracted using Convolutional Neural Networks (CNNs). Inspired by the two-stream network (TS-Net), we propose a multi-stream Convolutional Neural Network (CNN) architecture to recognize human actions. We additionally consider human-related regions that contain the most informative features. First, by improving foreground detection, the region of interest corresponding to the appearance and the motion of an actor can be detected robustly under realistic circumstances. Based on the entire detected hu...