no code implementations • IEEE Access ( Volume: 7 ) 2019 • Quanle Liu, Xiangjiu Che, Mei Bie
To solve this problem, we propose residual spatial-temporal attention network (R-STAN), a feed-forward convolutional neural network using residual learning and spatial-temporal attention mechanism for video action recognition, which makes the network focus more on discriminative temporal and spatial features.
Ranked #49 on Action Recognition on UCF101