STAB-GCN: A Spatio-Temporal Attention-Based Graph Convolutional Network for Group Activity Recognition

Fang Liu, Chunhua Tian, Jinzhong Wang (), Youwei Jin, Luxiang Cui and Ivan Lee
Additional contact information
Fang Liu: School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China
Chunhua Tian: School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China
Jinzhong Wang: Public Basic Course Teaching and Research Department, Shenyang Sport University, Shenyang 110102, China
Youwei Jin: Public Basic Course Teaching and Research Department, Shenyang Sport University, Shenyang 110102, China
Luxiang Cui: Sports Training College, Shenyang Sport University, Shenyang 110102, China
Ivan Lee: STEM, University of South Australia, Mawson Lakes 5095, Australia

Mathematics, 2023, vol. 11, issue 14, 1-13

Abstract: Group activity recognition is a central theme in many domains, such as sports video analysis, CCTV surveillance, sports tactics, and social scenario understanding. However, there are still challenges in embedding actors’ relations in a multi-person scenario due to occlusion, movement, and light. Current studies mainly focus on collective and individual local features from the spatial and temporal perspectives, which results in inefficiency, low robustness, and low portability. To this end, a Spatio-Temporal Attention-Based Graph Convolution Network (STAB-GCN) model is proposed to effectively embed deep complex relations between actors. Specifically, we leverage the attention mechanism to attentively explore spatio-temporal latent relations between actors. This approach captures spatio-temporal contextual information and improves individual and group embedding. Then, we feed actor relation graphs built from group activity videos into our proposed STAB-GCN for further inference, which selectively attends to the relevant features while ignoring those irrelevant to the relation extraction task. We perform experiments on three available group activity datasets, acquiring better performance than state-of-the-art methods. The results verify the validity of our proposed model and highlight the obstructive impacts of spatio-temporal attention-based graph embedding on group activity recognition.

Keywords: group activity recognition; sports video analysis; graph convolutional network; spatio-temporal attention (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/14/3074/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/14/3074/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:14:p:3074-:d:1192205

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().