An implementation of seminal CVPR 2016 paper: "A Hierarchical Deep Temporal Model for Group Activity Recognition."

A physics-guided hierarchical deep network (PhyRes-LSTM) framework, which integrates external knowledge with deep neural networks to guide the training process.

PyTorch implementation of a Relational Attention-Based Model for Group Activity Recognition — inspired by "A Hierarchical Deep Temporal Model for Group Activity Recognition (arXiv:1511.06040v2)"