|
|
In Association with
IEEE Computer Vision and Pattern Recognition (CVPR 2003)
Madison,
Wisconsin,
USA
June, 17 2003
Sponsored by IEEE Computer Society.
With recent advances in the analysis of digital video,
it is now becoming possible to look for high-level semantic events in video. The
analysis of events is important in a variety
of applications including surveillance, customer-relationship management (CRM),
vision-based human-computer
interaction, and content-based retrieval. Several
challenges exist with regard to the detection and
recognition of events. First, a good definition of what
constitutes an event itself is lacking. Secondly, understanding events seems to involve the detection and recognition of objects,
actions, and their evolving inter-relationships. Moreover, events are
often multi-modal, requiring the gathering of
evidence from information available in multiple media sources
such as video and audio. Even with the best techniques for visual
or audio scene analysis, event detection using individual cues
will continue to exhibit poor robustness in the foreseeable future on account of high detection errors. Further, the localization
of events through multi-modal
fusion will continue to face problems due
to conflicting indications given by the individual cues.
Event mining was introduced as a new field of research
in data mining in Event’ 2001. Following the success of this workshop at ICCV
‘2001, a continuation is being
proposed as Event’ 2003 to be part of CVPR ‘2003. It will be a forum to
highlight new research emerging in this field to address the above problems. We
are soliciting original papers that address a range of issues
in event detection and recognition in digital video including, but not restricted
by fallowing topics :
·
Event detection: Object detection, action detection, tracking.
·
Event
recognition:
Object recognition, action recognition, activity recognition.
·
Multi-modal
events:
Auditory events, audio-visual events, multi-modal fusion
·
Event
understanding:
Event labeling, computational theories of event perception
·
Event
retrieval:
Event representations, querying for events
·
Systems
& Applications:
Applications of event detection in areas such as surveillance, customer
relationship management, human
computer interaction, content-based retrieval, etc.
Accepted papers will be published by the IEEE in CD-ROM format and indexed in the IEEExplore website.
|
Ismail Haritaoglu |
IBM Almaden Research | |
|
Tanveer Syeda-Mahmood |
IBM Almaden Research |
| Robert Collins | CMU | |
| Jim Davis | Ohio State University | |
| Larry Davis | University of Maryland, College Park | |
| Ramani Duraiswami | University of Maryland, College Park | |
| Irfan Essa | Georgia Tech | |
| David Fleet | Xerox | |
| Tom Huang | University of Illinois, Urbana | |
| Anil Jain | University of Michigan, Ann Harbor | |
| Jim Little | University of British Columbia | |
| Steve Maybank | Reading University, UK | |
| Jun Ohya | Waseda University, JAPAN | |
| Nuria Oliver | Microsoft | |
| Mubarak Shah | University of Central Florida | |
| Murat Tekalp | University of Rochester | |
| Yaser Yacoob | University of Maryland, College Park | |
| H. Zhang | Microsoft | |
| Manuscript submission | January 31, 2003 | |
| Notification of acceptance | March 12, 2003 | |
| Final manuscript due | April 1, 2003 |
For further information please contact Ismail Haritaoglu (ismailh@almaden.ibm.com)