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 | Hulk(Finetune, ViT-L) | AP | 37.1 | — | Unverified |
| 2 | Hulk(Finetune, ViT-B) | AP | 35.6 | — | Unverified |
| 3 | HRFormer (HRFomer-B) | AP | 34.4 | — | Unverified |
| 4 | UniHCP (finetune) | AP | 33.6 | — | Unverified |
| 5 | HRNet (HRNet-w48 ) | AP | 33.5 | — | Unverified |
| 6 | HRNet (HRNet-w32) | AP | 32.3 | — | Unverified |
| 7 | HRFormer (HRFomer-S) | AP | 31.6 | — | Unverified |
| 8 | SimpleBaseline (ResNet-152) | AP | 29.9 | — | Unverified |
| 9 | SimpleBaseline (ResNet-101) | AP | 29.4 | — | Unverified |
| 10 | SimpleBaseline (ResNet-50) | AP | 28 | — | Unverified |