Pose is all you need: The pose only group activity recognition system (POGARS)
This addresses group activity recognition for video analysis, offering a more efficient and generalizable approach, though it is incremental in focusing on pose-only input.
The paper tackles group activity recognition by using only tracked human poses as input, achieving competitive results on a volleyball dataset and showing better generalization than RGB-based methods.
We introduce a novel deep learning based group activity recognition approach called the Pose Only Group Activity Recognition System (POGARS), designed to use only tracked poses of people to predict the performed group activity. In contrast to existing approaches for group activity recognition, POGARS uses 1D CNNs to learn spatiotemporal dynamics of individuals involved in a group activity and forgo learning features from pixel data. The proposed model uses a spatial and temporal attention mechanism to infer person-wise importance and multi-task learning for simultaneously performing group and individual action classification. Experimental results confirm that POGARS achieves highly competitive results compared to state-of-the-art methods on a widely used public volleyball dataset despite only using tracked pose as input. Further our experiments show by using pose only as input, POGARS has better generalization capabilities compared to methods that use RGB as input.