| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| 3D Human Pose Estimation | TotalCapture (Seen Cameras (1,3,5,7), Unseen Subjects (S4, S5)) | W2 Error25.8 | 17 | |
| 3D Human Pose Estimation | TotalCapture (Seen Cameras (1,3,5,7), Seen Subjects (S1, S2, S3)) | W29.3 | 17 | |
| Human Activity Recognition | TotalCapture | Accuracy72 | 16 | |
| 3D Human Pose Estimation | TotalCapture (Unseen Cameras (2,4,6,8), Overall) | MPJPE27 | 16 | |
| 3D Human Pose Estimation | TotalCapture (Unseen Cameras (2,4,6,8), Unseen Subjects (S4, S5)) | Error Metric W229.2 | 16 | |
| 3D Human Pose Estimation | TotalCapture (Unseen Cameras (2,4,6,8), Seen Subjects (S1, S2)) | W213.9 | 16 | |
| Sparse-sensor motion capture | TotalCapture | PE (Procrustes Error)3.07 | 8 | |
| Temporal Synchronization | TotalCapture (test) | MAE0.05 | 7 | |
| 3D Human Pose Estimation | TotalCapture (Unseen Subjects (S4, S5)) | W2 Error21.8 | 7 | |
| 3D Human Pose Estimation | TotalCapture (Seen Subjects (S1, S2, S3)) | W2 Error13 | 7 | |
| Rotation and Mesh Reconstruction | TotalCapture | SIP Error10.76 | 6 | |
| Motion Estimation | TotalCapture japan-office synthetic sequences 1.0 | MPJPE (Relative)4.13 | 5 | |
| Motion Estimation | TotalCapture flood-ground synthetic sequences 1.0 | r.MPJPE4.64 | 5 | |
| Video-to-IMU Retrieval | TotalCapture (subject-wise split) | R@168 | 4 | |
| IMU-to-Video Retrieval | TotalCapture (subject-wise split) | R@187 | 4 | |
| 3D Human Pose Estimation | TotalCapture | Mean Joint Error (mm)26 | 4 | |
| 3D Human Pose Estimation | TotalCapture 16 (S4 W2) | MPJPE (mm)45.07 | 3 | |
| 3D Human Pose Estimation | TotalCapture 16 (S4 A3) | MPJPE (mm)63.41 | 3 | |
| 3D Human Pose Estimation | TotalCapture 16 (S1 W2) | MPJPE (mm)49.62 | 3 | |
| 3D Human Pose Estimation | TotalCapture 16 (S1 FS3) | MPJPE (mm)53.29 | 3 | |
| 3D Human Pose Estimation | TotalCapture 16 (S1 A3) | MPJPE (mm)56.76 | 3 |