TY - GEN
T1 - Temporal Recursive Propagation Network for Action Recognition
AU - Li, Xu
AU - Zeng, Ming
AU - Wang, Jinjun
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/3
Y1 - 2020/3
N2 - Efficient spatio-temporal information modeling is the key to action recognition. Present state-of-the-art suffers from the trade-off of spatiotemporal information modeling capability and model complexity. In this paper, we propose a novel temporal recursive propagation network (TRP) which can efficiently encode and fusion spatiotemporal information. TRP Module can be inserted in existing 2D CNN architectures such as ResNet and MobileNet. Abundant experiments show that TRP enjoys the performance over 3D CNN at lower computational cost than 2D CNN. We evaluate the proposed TRP on the large action recognition benchmark dataset UCF-101. TRP outperforms the state-of-the-art methods on UCF-101 from scratch.
AB - Efficient spatio-temporal information modeling is the key to action recognition. Present state-of-the-art suffers from the trade-off of spatiotemporal information modeling capability and model complexity. In this paper, we propose a novel temporal recursive propagation network (TRP) which can efficiently encode and fusion spatiotemporal information. TRP Module can be inserted in existing 2D CNN architectures such as ResNet and MobileNet. Abundant experiments show that TRP enjoys the performance over 3D CNN at lower computational cost than 2D CNN. We evaluate the proposed TRP on the large action recognition benchmark dataset UCF-101. TRP outperforms the state-of-the-art methods on UCF-101 from scratch.
KW - Efficient Action Recognition
KW - Spatio-Temporal Modeling
KW - Video Classification
UR - https://www.scopus.com/pages/publications/85086359721
U2 - 10.1109/ICCEA50009.2020.00132
DO - 10.1109/ICCEA50009.2020.00132
M3 - 会议稿件
AN - SCOPUS:85086359721
T3 - Proceedings - 2020 International Conference on Computer Engineering and Application, ICCEA 2020
SP - 604
EP - 607
BT - Proceedings - 2020 International Conference on Computer Engineering and Application, ICCEA 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 International Conference on Computer Engineering and Application, ICCEA 2020
Y2 - 27 March 2020 through 29 March 2020
ER -