TY - GEN
T1 - Spatial-Temporal Separable Attention for Video Action Recognition
AU - Guo, Xi
AU - Hu, Yikun
AU - Chen, Fang
AU - Jin, Yuhui
AU - Qiao, Jian
AU - Huang, Jian
AU - Yang, Qin
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Convolutional neural networks (CNNs) have been proved as a efficient method for various of visual recognition tasks. However, it is more difficult for CNNs to capture long-range spatial-temporal cues in dynamic videos than in static images. Recent nonlocal neural networks attempt to overcome this problem by a self-attention mechanism, where pair-wise affinities for all the spatial-temporal positions are calculated. However, this introduces a substantial computational burden. In this paper, we propose a spatial-temporal separable attention module (STSAM) to reduce the computational complexity. The experimental results, based on the Kinetics 400 benchmark, show that our model achieves better performance but introduces less extra FLOPs than nonlocal neural networks.
AB - Convolutional neural networks (CNNs) have been proved as a efficient method for various of visual recognition tasks. However, it is more difficult for CNNs to capture long-range spatial-temporal cues in dynamic videos than in static images. Recent nonlocal neural networks attempt to overcome this problem by a self-attention mechanism, where pair-wise affinities for all the spatial-temporal positions are calculated. However, this introduces a substantial computational burden. In this paper, we propose a spatial-temporal separable attention module (STSAM) to reduce the computational complexity. The experimental results, based on the Kinetics 400 benchmark, show that our model achieves better performance but introduces less extra FLOPs than nonlocal neural networks.
KW - attention mechanism
KW - convolutional neural network
KW - nonlocal neural networks
KW - video action recognition
UR - https://www.scopus.com/pages/publications/85144627060
U2 - 10.1109/FAIML57028.2022.00050
DO - 10.1109/FAIML57028.2022.00050
M3 - 会议稿件
AN - SCOPUS:85144627060
T3 - Proceedings - 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2022
SP - 224
EP - 228
BT - Proceedings - 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2022
Y2 - 19 July 2022 through 21 July 2022
ER -