Hunting Group Clues with Transformers for Social Group Activity Recognition

12 Jul 2022  ·  Masato Tamura, Rahul Vishwakarma, Ravigopal Vennelakanti ·

This paper presents a novel framework for social group activity recognition. As an expanded task of group activity recognition, social group activity recognition requires recognizing multiple sub-group activities and identifying group members. Most existing methods tackle both tasks by refining region features and then summarizing them into activity features. Such heuristic feature design renders the effectiveness of features susceptible to incomplete person localization and disregards the importance of scene contexts. Furthermore, region features are sub-optimal to identify group members because the features may be dominated by those of people in the regions and have different semantics. To overcome these drawbacks, we propose to leverage attention modules in transformers to generate effective social group features. Our method is designed in such a way that the attention modules identify and then aggregate features relevant to social group activities, generating an effective feature for each social group. Group member information is embedded into the features and thus accessed by feed-forward networks. The outputs of feed-forward networks represent groups so concisely that group members can be identified with simple Hungarian matching between groups and individuals. Experimental results show that our method outperforms state-of-the-art methods on the Volleyball and Collective Activity datasets.

PDF Abstract

Results from the Paper

 Ranked #1 on Group Activity Recognition on Collective Activity (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Group Activity Recognition Collective Activity Tamura et al. Accuracy 96.5 # 1
Group Activity Recognition Volleyball Tamura et al. Accuracy 96.0 # 1


No methods listed for this paper. Add relevant methods here