4D Action Segmentation on HOI4D
83.97AccuracyPPTr + DiMP
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PPTr + DiMPBackbone=PPTr, Venue=This Paper, Input Frames=1502026.05 | 83.97 | 86.15 | 89.13 | 86.64 | 81.43 | |
| P4Transformer + DiMPBackbone=P4Transformer, Venue=This Paper, Input Frames=1502026.05 | 82.41 | 84.9 | 87.26 | 85.92 | 80.77 | |
| PPTr + C2PBackbone=PPTr, Venue=CVPR23, Input Frames=1502026.05 | 81.1 | 84 | 85.4 | 82.5 | 74.1 | |
| PPTr + VideoMAEBackbone=PPTr, Venue=NeurIPS22, Input Frames=1502026.05 | 78.6 | 80.2 | 81.9 | 78.7 | 69.9 | |
| PPTr + STRLBackbone=PPTr, Venue=ICCV21, Input Frames=1502026.05 | 78.4 | 79.1 | 81.8 | 78.6 | 69.7 | |
| PPTrBackbone=PPTr, Venue=ECCV22, Input Frames=1502026.05 | 77.4 | 80.1 | 81.7 | 78.5 | 69.5 | |
| P4Transformer + M2PSCBackbone=P4Transformer, Venue=ECCV24, Input Frames=150, Reproduced=true2026.05 | 75.9 | 77.1 | 78.4 | 74.1 | 65.9 | |
| P4Transformer + MaST-PreBackbone=P4Transformer, Venue=ICCV23, Input Frames=150, Reproduced=true2026.05 | 74.1 | 75.4 | 76.6 | 73.4 | 63.8 | |
| P4Transformer + C2PBackbone=P4Transformer, Venue=CVPR23, Input Frames=1502026.05 | 73.5 | 76.8 | 77.2 | 72.9 | 62.4 | |
| P4TransformerBackbone=P4Transformer, Venue=CVPR21, Input Frames=1502026.05 | 71.2 | 73.1 | 73.8 | 69.2 | 58.2 |