Third Workshop on
Use of Context in Vision Processing (UCVP)
https://sites.google.com/site/ucvp2011/home
in conjunction with
13th International Conference on Multimodal Interaction (ICMI)
Alicante, Spain, November 18, 2011

Call for Papers
Background

The 3rd Workshop on Use of Context in Video Processing (UCVP) offers a forum for the exchange of recent work on employing contextual information in problems of computer vision, and in particular, in video-based event and scene analysis. The workshop is organized following the success of the first two editions held along with ICMI-MLMI 2009 and CVPR 2010.

Recent efforts in defining ambient intelligence applications based on user-centric concepts, the advent of technology in different sensing modalities, as well as the expanding interest in multi-modal information fusion, situation-aware and dynamic vision processing algorithms have created a common motivation across different research disciplines to utilize context as a key enabler of application-oriented vision. Improved robustness, efficient use of sensing and computing resources, dynamic task assignment to different operating modules, as well as adaptation to event and user behavior models are among the benefits a vision processing system can gain through the utilization of contextual information.

Aims and scope

The proposed workshop aims to address the opportunities in incorporating contextual information in algorithm design for single or multi-camera vision systems, as well as systems in which vision is complemented with other sensing modalities such as audio, motion, proximity, occupancy, or location sensors each acting as a source of contextual data. Other sources of context can be inferences made based on using previous observations such as behavior models for the user, the environment, the event of interest, or data on prior performance by each camera. The objective of the workshop is to gather high-quality contributions describing leading-edge research in the use of context in video processing. The workshop further aims to stimulate interaction among the participants through a panel and group discussion.

Topics of interest to the workshop include:

• Methodology to define relevant sources of context:
o Multi-camera networks, multi-modal sensing systems
o Long-term observation, behavior models
o Spatial or temporal relationships of objects and events
o Interaction of user with objects
o Internet resources as knowledge-base for context extraction
• User-centric context and representation:
o User behavior model
o Demographic information
o User activity, location, expression, emotional state
o Stated preferences (explicit and implicit interfaces)
o Interaction between users
• Integration of context with visual processing:
o Context-driven event interpretation
o Active vision, multi-modal activation
o Service provision and switching based on context
o Response to user events and interaction with user
o Detection of abnormal behavior
o Active sensing, task assignment to different sensing modules
o Guided vision based on high-level reasoning
o User behavior modeling based on observations
o Applications in smart environments
o Human-Computer Interfaces

The workshop aims to encourage collaboration between researchers in different areas of computer vision, multimodal systems, and related disciplines. In addition, by introducing topics of emerging applications in smart environments, multi-camera networks, and multi-modal sensing, which offer sources of context, the workshop aims to extend the notion of context-based video processing to include high-level and application-driven information extraction and fusion.

Paper submission
The workshop solicits original and unpublished papers that address a wide range of issues concerning the use of context in vision processing. Authors should submit papers not exceeding 8 pages in total in the ICMI format (http://www.acm.org/icmi/2011/index.php?id=authors). Submissions must be sent in PDF to the following email address: xin.chen@navteq.com. Accepted papers will be presented at the workshop and be included in the conference proceeding. Note that they will not automatically appear in the ACM Digital Libraries. On the other hand, workshop authors will be invited to submit an extended version of their papers to the Journal of Ambient Intelligence and Smart Environments.
Important dates
Full paper submission: July 10, 2011
Notification of acceptance: August 12, 2011
Final paper submission: August 26, 2011
Workshop date: November 18, 2011

Registration
Please note that registration is needed in order to include an accepted paper in the proceedings. At least one author of each paper must register and attend the workshop to present the paper. Please refer to the main ICMI 2011 website for more details.

Program
The workshop will feature an opening keynote speech and a concluding panel discussion. The tentative panel discussion topic is “How to represent and model context information in vision processing”.

Organizing team

Hamid Aghajan (Stanford University, USA) – aghajan@stanford.edu
Xin Chen (NAVTEQ Corporation, USA) – xin.chen@navteq.com
Ying Li (IBM T. J. Watson Research, USA) – yingli@us.ibm.com
Ming-Hsuan Yang (UC Merced, USA) – mhyang@ucmerced.edu (Publicity Chair)