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 | OmniPose | PCK | 99.5 | — | Unverified |
| 2 | Soft-gated Skip Connections | PCK | 94.8 | — | Unverified |
| 3 | UniPose | PCK | 94.5 | — | Unverified |
| 4 | Residual Hourglass + ASR + AHO | PCK | 94.5 | — | Unverified |
| 5 | Chou et al. arXiv'17 | PCK | 94 | — | Unverified |
| 6 | Pyramid Residual Modules (PRMs) | PCK | 93.9 | — | Unverified |
| 7 | Stacked hourglass + Inception-resnet | PCK | 93.9 | — | Unverified |
| 8 | Multi-Context Attention | PCK | 92.6 | — | Unverified |
| 9 | FPD | PCK | 90.8 | — | Unverified |
| 10 | Part heatmap regression (ResNet-152) | PCK | 90.7 | — | Unverified |