Pose Estimation
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )
Papers
Showing 1–10 of 4228 papers
All datasetsCOCO test-devMPII Human PoseOCHumanLeeds Sports PosesCrowdPoseCOCO val2017AICCOCO (Common Objects in Context)InLocITOP front-viewJ-HMDBMPII Single Person
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | yolopose | AP50 | 90.3 | — | Unverified |
| 2 | ViTPose (ViTAE-G, ensemble) | AP | 81.1 | — | Unverified |
| 3 | ViTPose (ViTAE-G) | AP | 80.9 | — | Unverified |
| 4 | UDP-Pose-PSA(384x288) | AP | 79.5 | — | Unverified |
| 5 | PoseBH-H | AP | 79.5 | — | Unverified |
| 6 | 4xRSN-50 (ensemble) | AP | 79.2 | — | Unverified |
| 7 | CCM+ | AP | 78.9 | — | Unverified |
| 8 | UDP-Pose-PSA(256x192) | AP | 78.9 | — | Unverified |
| 9 | 4xRSN-50 | AP | 78.6 | — | Unverified |
| 10 | PCT (256x256) | AP | 78.3 | — | Unverified |