TY - GEN
T1 - SAGN
T2 - 11th ACM International Conference on Multimedia Retrieval, ICMR 2021
AU - Fu, Ziwang
AU - Liu, Feng
AU - Zhang, Jiahao
AU - Wang, Hanyang
AU - Yang, Chengyi
AU - Xu, Qing
AU - Qi, Jiayin
AU - Fu, Xiangling
AU - Zhou, Aimin
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/9/1
Y1 - 2021/9/1
N2 - With the continuous development and popularity of depth cameras, skeleton-based human action recognition has attracted people's wide attention. Graph Convolutional Network (GCN) has achieved remarkable performance. However, the existing methods do not better consider the semantic characteristics, which can help to express the current concept and scene information. Semantic information can also help with better granularity classification. In addition, most of the existing models require a lot of computation. What's more, adaptive GCN can automatically learn the graph structure and consider the connections between joints. In this paper, we propose a relatively less computationally intensive model, which combines semantic and adaptive graph network (SAGN) for skeleton-based human action recognition. Specifically, we mainly combine the dynamic characteristics and bone information to extract the data, taking the correlation between semantics into the model. In the training process, SAGN includes an adaptive network so that we can make attention mechanism more flexible. We design the Convolutional Neural Network (CNN) for feature extraction on the time dimension. The experimental results show that SAGN achieves the state-of-the-art performance on NTU-RGB+D 60 and NTU-RGB+D 120 datasets. SAGN can promote the study of skeleton-based human action recognition. The source code is available at https://github.com/skeletonNN/SAGN.
AB - With the continuous development and popularity of depth cameras, skeleton-based human action recognition has attracted people's wide attention. Graph Convolutional Network (GCN) has achieved remarkable performance. However, the existing methods do not better consider the semantic characteristics, which can help to express the current concept and scene information. Semantic information can also help with better granularity classification. In addition, most of the existing models require a lot of computation. What's more, adaptive GCN can automatically learn the graph structure and consider the connections between joints. In this paper, we propose a relatively less computationally intensive model, which combines semantic and adaptive graph network (SAGN) for skeleton-based human action recognition. Specifically, we mainly combine the dynamic characteristics and bone information to extract the data, taking the correlation between semantics into the model. In the training process, SAGN includes an adaptive network so that we can make attention mechanism more flexible. We design the Convolutional Neural Network (CNN) for feature extraction on the time dimension. The experimental results show that SAGN achieves the state-of-the-art performance on NTU-RGB+D 60 and NTU-RGB+D 120 datasets. SAGN can promote the study of skeleton-based human action recognition. The source code is available at https://github.com/skeletonNN/SAGN.
KW - Adaptive GCN
KW - Data fusion
KW - Semantic information
KW - Skeleton-based human action recognition
UR - https://www.scopus.com/pages/publications/85114877241
U2 - 10.1145/3460426.3463633
DO - 10.1145/3460426.3463633
M3 - 会议稿件
AN - SCOPUS:85114877241
T3 - ICMR 2021 - Proceedings of the 2021 International Conference on Multimedia Retrieval
SP - 110
EP - 117
BT - ICMR 2021 - Proceedings of the 2021 International Conference on Multimedia Retrieval
PB - Association for Computing Machinery, Inc
Y2 - 21 August 2021 through 24 August 2021
ER -