CVPR 2007 EHuM2 Workshop CALL FOR PARTICIPATION

EHuM2: 2nd Workshop on Evaluation of Articulated Human Motion and Pose
Estimation
With IEEE Computer Vision and Pattern Recognition (CVPR) 2007
June 22, 2007, Minneapolis, MN
http://www.cs.brown.edu/people/ls/ehum2/

OVERVIEW:
There has been a large body of work developed in the last 10 years on
the human pose estimation and tracking from video. 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.

DATASET:
The HumanEva dataset contains multiple calibrated video sequences
(grayscale and color) that are synchronized with 3D body poses obtained
from a motion capture system. The database contains multiple subjects
performing a variety of common actions (e.g. walking, jogging,
gesturing, etc.). The error metrics for computing error in 2D and 3D
pose will be provided to participants. The dataset contains training,
validation and testing (with withheld ground truth) sets.

SCOPE:
The workshop program will consist of papers, 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);
- 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submissions of both original unpublished works as well as surveys where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 writeup
describing experimental analysis with the EHuM dataset.

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.


DATES:
Call for participation: January 30, 2007
Submission deadline: April 20, 2007
Notification to authors: May 18, 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.

ORGANIZING COMMITTEE:
L. Sigal (Brown University)
M. Black (Brown University)
H. Haussecker (Intel Research)

PROGRAM COMMITTEE:
A. Agarwal (Microsoft Research)
S. Carlsson (KTH)
T. Darrell (MIT)
J. Davis (UC Santa Cruz)
L. Davis (U of Maryland)
D. Fleet (U of Toronto)
D. Forsyth (UIUC)
P. Fua (EPFL)
D. Huttenlocher (Cornell U)
R. Nevatia (USC)
D. Ramanan (TTI-C)
J. Rehg (Georgia Tech)
S. Sclaroff (Boston U)
C. Sminchisescu (TTI-C)
P. Torr (Oxford Brookes)
B. Triggs (INRIA)
Y. Wu (Northwestern U)
M.-H. Yang (Honda Research)

INVITED SPEAKERS:
D. Fleet (U of Toronto)
J. Hodgins (CMU) [tentative]