DM-CTSA: a discriminative multi-focused and complementary temporal/spatial attention framework for action recognition |
| |
Authors: | Tong Ming Yan Kaibo Jin Lei Yue Xing Li Mingyang |
| |
Affiliation: | 1.School of Electronic Engineering, Xidian University, Xi’an, 710071, China ; |
| |
Abstract: | Neural Computing and Applications - Video-based human action recognition remains a challenging task. There are three main limitations: (1) Most works are only restricted to single temporal scale... |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |