R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition

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.

Action Recognition Temporal Action Localization