Pose is all you need: The pose only group activity recognition system (POGARS)
arXiv:2108.04186 · doi:10.1007/s00138-022-01346-2
Abstract
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.
arXiv comment12 pages, 7 figures
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- How transferable are features in deep neural networks?
- Recurrent Models of Visual Attention
- Stacked Hourglass Networks for Human Pose Estimation
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- Pose-conditioned Spatio-Temporal Attention for Human Action Recognition
- Skeleton-based Relational Reasoning for Group Activity Analysis
- Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks
- Action Machine: Rethinking Action Recognition in Trimmed Videos
- A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition
- Deep Keyframe Detection in Human Action Videos
- Learning Person Trajectory Representations for Team Activity Analysis
- Convolutional Relational Machine for Group Activity Recognition