TY - GEN
T1 - Skeleton-Based Online Action Detection with Temporal Enhancement
AU - Ying, Boyu
AU - Xiang, Junyuan
AU - Zheng, Wei
AU - Wang, Zhiyong
AU - Ren, Weihong
AU - Luo, Shuli
AU - Liu, Honghai
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - Online action detection focuses on recognizing actions happening in the latest frames of streaming video. Given the strong correlation between human skeletons and actions, many researchers have attempted to use skeletons for online action detection. Recently, spatio-temporal graph convolutional methods achieve good action modeling effects, but they have limited capability for detecting actions in the latest frames. In this paper, we introduce a temporal enhancement technique to optimize the performance of skeleton-based online action detection, involving a temporal feature enhancement module and a motion difference module. The temporal feature enhancement module, modified based on Transformer, enhances the latest features temporally. The motion difference module introduces motion features into the network. Experimental results demonstrate that our method is competitive.
AB - Online action detection focuses on recognizing actions happening in the latest frames of streaming video. Given the strong correlation between human skeletons and actions, many researchers have attempted to use skeletons for online action detection. Recently, spatio-temporal graph convolutional methods achieve good action modeling effects, but they have limited capability for detecting actions in the latest frames. In this paper, we introduce a temporal enhancement technique to optimize the performance of skeleton-based online action detection, involving a temporal feature enhancement module and a motion difference module. The temporal feature enhancement module, modified based on Transformer, enhances the latest features temporally. The motion difference module introduces motion features into the network. Experimental results demonstrate that our method is competitive.
KW - Online action detection
KW - Skeleton-based
KW - Temporal action modeling
UR - https://www.scopus.com/pages/publications/105005483174
U2 - 10.1007/978-981-96-5084-2_10
DO - 10.1007/978-981-96-5084-2_10
M3 - 会议稿件
AN - SCOPUS:105005483174
SN - 9789819650835
T3 - Communications in Computer and Information Science
SP - 145
EP - 156
BT - Emotional Intelligence - Second CSIG Conference, CEI 2024, Proceedings
A2 - Huang, Xiaohua
A2 - Mao, Qirong
PB - Springer Science and Business Media Deutschland GmbH
T2 - 2nd CSIG Conference on Emotional Intelligence, CEI 2024
Y2 - 6 December 2024 through 8 December 2024
ER -