ECCV 2018 PoseTrack DensePose Challenge

Organized by vkhalidov - Current server time: Nov. 14, 2018, 11:34 a.m. UTC

Previous

test
June 30, 2018, midnight UTC

Current

test
June 30, 2018, midnight UTC

End

Competition Ends
Aug. 19, 2018, 7:59 a.m. UTC

ECCV 2018 PoseTrack DensePose Challenge

The ECCV PoseTrack DensePose Challenge is designed to push the state of the art in dense human pose tracking. The task of dense human pose tracking comprises

  • human body detection,
  • human body segmentation,
  • mapping all image pixels that belong to a human body to the 3D surface of the body,
  • tracking the estimated mappings over time.

Schematic representation of the task is given in Figure 1.

Figure 1. Dense human pose estimation and tracking involves human body detection, human body segmentation, mapping all pixels that belong to a human body to the 3D surface of the body and tracking the estimated mappings over time.

This challenge is part of the PoseTrack Workshop at ECCV 2018. For further details about the joint workshop please visit the workshop website. Please also take a look at the concurrent PoseTrack challenges on Articulated Human Pose Estimation and Tracking and 3D Human Pose Estimation.

To participate, you can find instructions on the PoseTrack DensePose page. In particular, please see the overview, download, data format, results format, upload and evaluation pages for more detail.

The COCO DensePose API is used to evaluate results of the PoseTrack DensePose Challenge. The software uses both candidate and reference point correspondences defined by body part index and intrinsic 2D coordinates on the body part, and applies the Average Precision evaluation metric. For more details please check evaluation procedure, results format and upload instructions pages.

val

Start: June 30, 2018, midnight

Description: The val evaluation server for PoseTrack DensePose. We encourage use of val to perform validation experiments; for publication, please evaluate your results on test. Results submitted to val will NOT be posted to the public leaderboard. JSON file with the results should be named posetrack_val_[alg]_results.json, where [alg] with your algorithm name; it should be compressed into a zip file named posetrack_val_[alg]_results.zip.

test

Start: June 30, 2018, midnight

Description: The test evaluation server for PoseTrack DensePose. We encourage use of test to report evaluation results for publication. Please choose "Submit to Leaderboard" if you want your submission to be appeared on the leaderboard. JSON file with the results should be named posetrack_test_[alg]_results.json, where [alg] with your algorithm name; it should be compressed into a zip file named posetrack_test_[alg]_results.zip.

Competition Ends

Aug. 19, 2018, 7:59 a.m.

You must be logged in to participate in competitions.

Sign In
# Username Score
1 ML_LAB 0.30
2 Molength 0.29
3 DensePose_R101_FPN_32x8d_s1x_e 0.29