Group Activity Recognition On Collective
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Tamura et al. | 96.5 | Hunting Group Clues with Transformers for Social Group Activity Recognition | - |
| Deng et al. | 81.2 | Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition | - |
| GT (Inception-v3) | 91 | Learning Actor Relation Graphs for Group Activity Recognition | |
| COMPOSER | 96.2 | COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality | |
| CHASE(CTR-GCN) | 89.61 | CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition | |
| H-LSTCM | 83.75 | Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition | - |
0 of 6 row(s) selected.