Call for Papers
First IEEE Workshop on Face Processing in Video (FPIV'04)
in conjunction with
IEEE International Conference on Computer Vision and Pattern Recognition
(CVPR'04)
Washington, D.C.
June 26- June 27, 2004
Conference web-site: http://www.visioninterface.net/fpiv04
AIMS AND SCOPE
Face processing is an area of research dedicated to the extraction and
manipulation of information about human faces. It deals with such
problems as face detection, tracking, recognition, coding, etc. as well
as their applications.
Video is becoming ubiquitous and very affordable, and there is growing
demand on vision-based human-oriented applications, ranging from
security and industry for disabled to computer-human interaction and
video annotation. Therefore, more and more research effort is being put
on face processing in video, which is very different from face
processing in still imaginary in terms of the nature of data processed.
On one hand, because of real-time, bandwidth and environmental
constraints, video images are of rather modest resolution and quality,
as compared to photo-images. On the other hand, such a seeming
deficiency of video is compensated by the abundance of images due to the
dynamic nature of video. Video processing and understanding also has
many parallels with biological vision, which provides additional
insights and solutions to the problem.
Therefore, it is important to develop approaches other than those
developed for still imagery which would make use of the advantages of
video for face processing. With this goal in mind, the FPIV'04 workshop
is aimed at providing a forum for scientists from different backgrounds:
biological vision, computer vision, pattern recognition, machine
learning, HCI, etc. - to share their experiences and discuss the
problems, solutions and applications of Face Processing in Video.
The workshop will consist of one day of oral presentations and a talk
from an invited speaker on a synergy of biological and computer vision.
Paper submission
Although any paper analyzing video for the presence of information about
faces may be submitted, the preference will be given to those papers
which clearly indicate in the abstract a) the research areas of the
paper and b) what the paper contributions are. Application-oriented
papers are as much welcome as theoretical papers.
The suggested research areas are listed below, but other topics dealing
with the face in video scenario are welcome.
neurobiological and neurocomputational approaches to visual
perception and recognition
synergy between biological and computer vision
face segmentation and detection in video
face tracking and multiple faces tracking
face memorization, classification recognition from video
face biometrics and face modeling, 3d face models
facial features for tracking and recognition
face representation, canonical face models, face in video
databases
face synthesis and mimicking
facial expression recognition and classification, and
representation
fusing different modalities of video information (motion,
colour, intensity)
performance evaluation for face in video problems
face detection/tracking/recognition in multicamera setups
including stereo
face detection/tracking/recognition in panoramic video
combining video and audio for speaker face
detection/tracking/recognition
face-based multi-media, games, and computer-human interaction
perceptual face-controlled interfaces
face processing for video-conferencing
face processing for avatars and computer-generated communication
programs
face processing for immersive and collaborative environments
face processing for industry for disabled
face processing for augmented and virtualized reality
face processing for security and surveillance
face processing for encoding and annotating video
Papers should not exceed 6 double-column pages. Only original
manuscripts will be considered. Dual submission with CVPR is not
permitted. Instead, if a relevant paper on object tracking, recognition
etc has been submitted to CVPR, a related, but focused on the face as of
an object of interest and video as of a media can be submitted to the
workshop. This policy is intended to encourage participation from
authors whose papers are accepted in CVPR as well as those that are not.
Reviewing will be blind circular. By submitting a paper, each author
agrees to review at least 3 other submissions. This procedure has
produced quality, useful reviews in previous CVPR workshops. As
reviewers, authors must comply with the reviewing schedule below. In
addition, each paper will be reviewed by the program committee. Given
the exploratory nature of the workshop, reviews will emphasize the
novelty of the ideas and clarity of presentation.
The paper must not include any information that would indicate the
author's identity (references to authors' previous work should be left
blank). Papers must be submitted in the same format as for CVPR and
submitted as pdf files, by emailing to the Program Chair. In an email
accompanying the paper, authors should supply
1) the title of the paper
2) keywords relating to the paper,
3) the names and affiliations of the authors
4) (!) areas of expertise of the authors (for circular reviewing), and
5) the name of the contact author
IMPORTANT DATES:
Full Paper Submission : January 17, 2004
Papers Distributed for Review: January 20, 2004
Reviews due: February 25, 2004
Notification to acceptance : March 2, 2004
camera ready copy: April 4, 2004
PROGRAM ORGANIZER:
Dmitry O. Gorodnichy, NRC-CNRC, Canada
Email: fpiv04 AT visioninterface.net (dmitry.gorodnichy AT nrc-cnrc.gc.ca)
PROGRAM COMITTEE:
Bernhard Fröba, Fraunhofer-Institut, Germany
Laurent Itti, U. of Southern California, USA
Takeo Kanade, CMU, USA
Josef Kittler, University of Surrey, UK
Ernst Kussul, U. Nacional Autonoma de Mexico, Mexico
Stan Z. Li, Microsoft Research, China
Michael J. Lyons, ATR Media Information Science Labs, Japan
Marc Parizeau, U. Laval, Canada
Maximilian Riesenhuber, Georgetown U., USA
Gerhard Roth, NRC-CNRC, Canada
Chris Solomon, University of Kent at Canterbury, UK
Jean-Christophe Terrillon, Softopia Japan Foundation, Japan
Matthew Turk, UCSB, USA
Lijun Yin, Binghamton University, USA