EHuM2: 2-nd Workshop on Evaluation of Articulated Human Motion and Pose Estimation

(Workshop at CVPR 2007)

Home Schedule Registration HumanEva Dataset Submissions

Frontpage Template Resources


- CFP (pdf, ps)

- Register to obtain dataset.



Organizing Committee:

Leonid Sigal (Brown U)

Michael J. Black (Brown U)

Horst Haussecker (Intel)


Program Committee:

Ankur Agarwal (Microsoft Research)

Stefan Carlsson (KTH)
Trevor Darrell (MIT)
James Davis (UC Santa Cruz)
Larry Davis (U of Maryland)
David Fleet (U of Toronto)
David Forsyth (UIUC)
Pascal Fua (EPFL)
Horst Haussecker (Intel)
Daniel Huttenlocher (Cornell U)
Ram Nevatia (USC)
Deva Ramanan (TTI-C)
James Rehg (Georgia Tech)

Stan Sclaroff (Boston U)
Cristian Sminchisescu (TTI-C)

Philip Torr (Oxford Brookes)
Bill Triggs (INRIA)
Ying Wu (Northwestern U)

Ming-Hsuan Yang (Honda)


Invited Speakers:

David Fleet (U of Toronto)





  Overview: There has been a large body of work developed in the last 10 years on the human pose estimation and tracking from video. Many of these methods are based on well founded statistical models and machine learning techniques. Progress however has been limited because of the lack of common datasets and error metrics for quantitative comparison. The goal of this workshop is to (1) establish the current state of the art in the human pose estimation and tracking from single and multiple camera views, (2) discuss future directions in the field, and (3) introduce a benchmark database and error metrics for comparing current and future methods. To this end a new (HumanEva) dataset has been introduced.  
Scope: Workshop program will consist of papers, posters, invited talks and a discussion panel. The list of possible topics includes (but is not limited to) the following:
  • Tracking and pose estimation (in 2D and 3D);
  • Articulated body models;
  • Priors for human motion and dynamics;
  • Appearance models;
  • Discriminative and generative approaches for articulated pose recovery;
  • Quantitative metrics for evaluation of pose estimation and tracking.
Submissions: All submissions will be required to use the dataset provided and the on-line evaluation system for evaluation of results. Due to the retrospective and prospective nature of the workshop, we will encourage submissions of both original unpublished works as well as surveys where prior approaches are evaluated using the data and the metrics provided. Submissions should contain an extensive experimental section and enough algorithmic details to allow reproducibility of results. We invite submissions of full length 8-page papers in the 2-column CVPR style.

We encourage authors of papers at the main CVPR conference to present an evaluation of their method at the workshop. For CVPR-accepted papers, authors should submit (1) a copy of the CVPR paper; (2) a brief write-up describing experimental analysis with the EHuM dataset. Workshop acceptances will be determined based on the quality of the experimental analysis. It is expected that authors presenting at both the main meeting and the workshop will focus their workshop presentations on the experimental analysis.

Reviewing Process: All papers will be subject to a double-blind review process by a program committee of leading international researchers with experience in human motion and pose estimation. Each paper will be reviewed by 2 members of the program committee. Based on these reviews, the workshop organizers will decide on acceptance and presentation mode (oral/spotlights). Instead of having a poster session, we propose to have short oral spotlight presentations.
Important Dates:
Call for participation: January 23, 2007
Submission deadline: April 20, 2007      Extended: 11:59pm, April 24
Notification to authors: May 18, 2007       Extended: May 25
Final submission deadline (of accepted papers): June 1, 2007
Workshop in Minneapolis, Minnesota: June 22, 2007
Submission of revised IJCV manuscripts: August, 2007
Proceedings: In lieu of a proceedings, authors will be invited to submit extended versions of their papers to a special issue of International Journal of Computer Vision (IJCV) on human pose estimation and tracking with a deadline in August 2007.


Copyright Leonid Sigal. All Rights Reserved. Brown University