Learning Group Activities from Skeletons without Individual Action Labels

14 May 2021  ·  Fabio Zappardino, Tiberio Uricchio, Lorenzo Seidenari, Alberto del Bimbo ·

To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions. Hierarchical models obtain the best results in group activity recognition but require fine grained individual action annotations at the actor level. In this paper we show that using only skeletal data we can train a state-of-the art end-to-end system using only group activity labels at the sequence level. Our experiments show that models trained without individual action supervision perform poorly. On the other hand we show that pseudo-labels can be computed from any pre-trained feature extractor with comparable final performance. Finally our carefully designed lean pose only architecture shows highly competitive results versus more complex multimodal approaches even in the self-supervised variant.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Group Activity Recognition Volleyball Zappardino et al. Accuracy 91.0 # 8
Group Activity Recognition Volleyball Zappardino et al. (SSAL) Accuracy 89.4 # 9


No methods listed for this paper. Add relevant methods here