Challenge Results can be found here

PoseTrack is a joint project of the Max Planck Institute for Informatics, University of Bonn and the PoseTrack team.

MPII UniBonn

The workshop is supported by nVidia, Facebook Reality Labs and Playment
Nvidia       Facebook      Playment

About the Workshop

The goal of this workshop is to advance the state of the art in articulated people tracking and visual human analysis. Building on the experience of the previous iteration of this workshop organized at ICCV'17, we introduce an extended version of the PoseTrack benchmark for articulated people tracking. The extended benchmark will double the amount of annotated data, laying emphasis on common challenging cases for existing methods. In addition to the PoseTrack challenge we will be hosting additional challenges on dense pose estimation in collaboration with the authors of the DensePose project and on 3D human pose estimation in collaboration with the Human3.6M team. Finally, the workshop will include a diverse program featuring keynote speakers, poster presentations, and a discussion panel to provide a forum for the exchange of ideas among the researchers working in the area of visual human analysis.

What is Our Goal?

The main goals of this workshop will be to introduce new challenges to the PoseTrack Workshop series. The planned panel discussion with world’s leading experts on this problem will be a fruitful input and source of ideas for all participants. This will be the second edition in the PoseTrack series. We as organizers expect to receive valuable feedback from users and from the community on how to improve the benchmark. A few potential issues for the discussion are

  • Where are we in terms of solving the problem of human pose tracking?
  • What are positive and negative points of the PoseTrack dataset?
  • Are current evaluation metrics representative of the solution quality?
  • What are the major failure modes of current methods and how can these be eliminated?

Event Schedule

Saturday, September 8, 2018 (afternoon)
Location: TU-München, Arcisstr. 21, 80333 München.
Talks are in room N1070ZG. Posters are in room 2605.

13:20 - 13:30Introduction 
13:30 - 14:00Invited TalkChristian Theobalt (MPI Informatik)
14:00 - 14:30Invited TalkGeorge Papandreou (Google)
14:30 - 15:00Challenge Results 
15:00 - 15:15Spotlight Presentations by the Winners 
15:15 - 15:45Poster Session and Coffee Break 
15:45 - 16:15Invited TalkCristian Sminchisescu (Lund University and Google)
16:15 - 16:45Invited TalkIasonas Kokkinos (UCL and Facebook AI Research)
16:45 - 17:15Closing Remarks & Discussion 

Challenges

1. PoseTrack Challenge on Articulated Human Pose Estimation and Tracking

In this challenge it will be required to estimate and track 2D articulated poses of multiple people in real-world videos. Both single-frame pose estimation accuracy as well as articulated tracking accuracy will be evaluated and a winner will be determined in each category. The videos in this challenge will be similar to those included in the PoseTrack'17 benchmark at ICCV'17. To further improve the benchmark this year we will double the dataset size.

New: The PoseTrack18 dataset and evaluation code are now available here.

Organizers: Mykhaylo Andriluka, Umar Iqbal, Anon Milan, Eldar Insafutdinov, Christoph Lassner, Siyu Tang, Leonid Pishchulin, Juergen Gall, Bernt Schiele


Full Benchmark Release and Evaluation Server Opening: August 6th, 2018
Results Submission: August 31st, 2018

2. DensePose-PoseTrack challenge on dense pose estimation in time

In this challenge the participants will be required to estimate dense correspondences between people videos and a 3D body shape model. The challenge is based on the data from PoseTrack'17 benchmark that has been annotated with dense pose correspondences. More details about the task are available at densepose.org

New: The DensePose-PoseTrack dataset and evaluation code are now available here.

Evaluation server is now open for submissions.

Organizers: Rıza Alp Güler, Natalia Neverova and Iasonas Kokkinos


Train+Val Pre-Release: July 2nd, 2018
Full Benchmark Release and Evaluation Server Opening: July 15th, 2018
Results Submission: August 18th, 2018

3. 3D Human Pose Estimation Challenge

In this challenge the participants are required to estimate poses of people in 3D. The challenge is based on the popular Human3.6 benchmark which offers the possibility of estimating 2D and 3D skeletal joint positions, joint angles, semantic segmentation of body parts, as well as 3D human shape and depth, and will in addition provide and evaluate dense correspondences similar to the DensePose challenge.

New: The dataset for the 3D human pose estimation challenge is now available here.

Organizers: Andrei Zanfir, Elisabeta Marinoiu, Alin Popa, MIhai Zanfir, Vlad Olaru and Cristian Sminchisescu


Train+Val Pre-Release: July 9th, 2018
Full Benchmark Release and Evaluation Server Opening: July 22nd, 2018
Results Submission: August 18th, 2018

Challenge Deadline
August 31

Paper/Abstract Submission
August 25

Notification of Acceptance
September 2

Workshop

September 8

Speakers

George Papandreou

George Papandreou

Google

Iasonas Kokkinos

Iasonas Kokkinos

University College London & Facebook AI Research

Christian Theobalt

Christian Theobalt

MPI Informatik

Cristian Sminchisescu

Cristian Sminchisescu

Lund University & Google

People

Organizers