Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping

MVA 2021  ·  Chihiro Nakatani, Kohei Sendo, Norimichi Ukita ·

This paper proposes joint learning of individual action recognition and people grouping for improving group activity recognition. By sharing the information between two similar tasks (i.e., individual action recognition and people grouping) through joint learning, errors of these two tasks are mutually corrected. This joint learning also improves the accuracy of group activity recognition. Our proposed method is designed to consist of any individual action recognition methods as a component. The effectiveness is validated with various IAR methods. By employing existing group activity recognition methods for ensembling with the proposed method, we achieved the best performance compared to the similar SOTA group activity recognition methods.



Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Group Activity Recognition Volleyball Joint learning (5-fusion) Accuracy 93.3 # 5


No methods listed for this paper. Add relevant methods here