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 | SimpleBaseline + HANet | Mean PCK@0.2 | 99.6 | — | Unverified |
| 2 | DeciWatch | Mean PCK@0.2 | 99 | — | Unverified |
| 3 | LSTM PM | Mean PCK@0.2 | 93.6 | — | Unverified |
| 4 | CPM | Mean PCK@0.2 | 91.9 | — | Unverified |
| 5 | UniTrack_i18 | Mean PCK@0.2 | 80.5 | — | Unverified |