SAGN: Semantic adaptive graph network for skeleton-based human action recognition

  • Ziwang Fu
  • , Feng Liu*
  • , Jiahao Zhang
  • , Hanyang Wang
  • , Chengyi Yang
  • , Qing Xu
  • , Jiayin Qi
  • , Xiangling Fu*
  • , Aimin Zhou
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationICMR 2021 - Proceedings of the 2021 International Conference on Multimedia Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages110-117
Number of pages8
ISBN (Electronic)9781450384636
DOIs
StatePublished - 1 Sep 2021
Event11th ACM International Conference on Multimedia Retrieval, ICMR 2021 - Taipei, Taiwan, Province of China
Duration: 21 Aug 202124 Aug 2021

Publication series

NameICMR 2021 - Proceedings of the 2021 International Conference on Multimedia Retrieval

Conference

Conference11th ACM International Conference on Multimedia Retrieval, ICMR 2021
Country/TerritoryTaiwan, Province of China
CityTaipei
Period21/08/2124/08/21

Keywords

  • Adaptive GCN
  • Data fusion
  • Semantic information
  • Skeleton-based human action recognition

Fingerprint

Dive into the research topics of 'SAGN: Semantic adaptive graph network for skeleton-based human action recognition'. Together they form a unique fingerprint.

Cite this