# Video Pose Propagation on PoseTrack 2017 (val)

Source: [Video Pose Propagation on PoseTrack 2017 (val)](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:46:25.023Z

Evaluation of Video Pose Propagation performance on the validation split of the PoseTrack 2017 dataset, reporting metrics for individual body joints (Head, Shoulder, Elbow, Wrist, Hip, Knee, Ankle) and the mean score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Video Pose Propagation |
| Dataset (including any stated split) | PoseTrack 2017 (val) |
| Metric | Head |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Head](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Head>): Higher is better; unit: PERCENT.

- [Shoulder](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Shoulder>): Higher is better; unit: PERCENT.

- [Elbow](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Elbow>): Higher is better; unit: PERCENT.

- [Wrist](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Wrist>): Higher is better; unit: PERCENT.

- [Hip](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Hip>): Higher is better; unit: PERCENT.

- [Knee](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Knee>): Higher is better; unit: PERCENT.

- [Ankle](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Ankle>): Higher is better; unit: PERCENT.

- [Mean Score](<https://www.sota2.com/research/sota/video-pose-propagation-on-posetrack-2017-val.md?metric=Mean%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Head | Result date | Report paper |
| --- | --- | --- | --- |
| PoseWarper | 86.3 | Not recorded | 68fa66c81e209131cea12372 |
| PoseWarper | 86.1 | Not recorded | 68fa66c81e209131cea12372 |
| PoseWarper | 86.1 | Not recorded | 68fa66c81e209131cea12372 |
| PoseWarper | 86 | Not recorded | 68fa66c81e209131cea12372 |
| PoseWarper | 85.8 | Not recorded | 68fa66c81e209131cea12372 |
| PoseWarper | 85 | Not recorded | 68fa66c81e209131cea12372 |
| Optical Flow Propagation (FlowNet2) | 82.7 | Not recorded | 68fa66c81e209131cea12372 |
| Pseudo-labeling w/ HRNet | 79.1 | Not recorded | 68fa66c81e209131cea12372 |
| Optical Flow Propagation (Farneback) | 76.5 | Not recorded | 68fa66c81e209131cea12372 |

### PoseWarper

Head: 86.3. Result ID: 698d06318b517eb4331e6db0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Implementation](<https://github.com/facebookresearch/PoseWarper>)

Recorded evaluation configuration: {"dilated convolutions":"4"}. This record does not assert independent reproduction.

### PoseWarper

Head: 86.1. Result ID: 698d06318b517eb4331e6dac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Implementation](<https://github.com/facebookresearch/PoseWarper>)

Recorded evaluation configuration: {"dilated convolutions":"none"}. This record does not assert independent reproduction.

### PoseWarper

Head: 86.1. Result ID: 698d06318b517eb4331e6daf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Implementation](<https://github.com/facebookresearch/PoseWarper>)

Recorded evaluation configuration: {"dilated convolutions":"3"}. This record does not assert independent reproduction.

### PoseWarper

Head: 86. Result ID: 698d06318b517eb4331e6db1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Implementation](<https://github.com/facebookresearch/PoseWarper>)

Recorded evaluation configuration: {"dilated convolutions":"5"}. This record does not assert independent reproduction.

### PoseWarper

Head: 85.8. Result ID: 698d06318b517eb4331e6dae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Implementation](<https://github.com/facebookresearch/PoseWarper>)

Recorded evaluation configuration: {"dilated convolutions":"2"}. This record does not assert independent reproduction.

### PoseWarper

Head: 85. Result ID: 698d06318b517eb4331e6dad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Implementation](<https://github.com/facebookresearch/PoseWarper>)

Recorded evaluation configuration: {"dilated convolutions":"1"}. This record does not assert independent reproduction.

### Optical Flow Propagation (FlowNet2)

Head: 82.7. Result ID: 698d06318b517eb4331e6dab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62fe1e209131ce9fc1c1.md>)

Recorded evaluation configuration: {"Optical Flow Algorithm":"FlowNet2"}. This record does not assert independent reproduction.

### Pseudo-labeling w/ HRNet

Head: 79.1. Result ID: 698d06318b517eb4331e6da9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65661e209131cea0a048.md>)

[Implementation](<https://github.com/leoxiaobin/deep-high-resolution-net.pytorch>)

Recorded evaluation configuration: {"Backbone":"HRNet"}. This record does not assert independent reproduction.

### Optical Flow Propagation (Farneback)

Head: 76.5. Result ID: 698d06318b517eb4331e6daa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12372.md>)

Recorded evaluation configuration: {"Optical Flow Algorithm":"Farneback"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.