We have organized a two day academic and industry workshop at AAAI 2011 (August 7th and 8th, 2011) in San Francisco, to explore techniques and languages for context representation within a task / activity. This is a great opportunity to create an international consortium to work towards common exchange protocols for task / activity models and context representation for assistive cognition devices in the digital workplace and the consumer playspace.
PDF Version: Call_for_Participation_ActivityContext_AAAI-11_Full
Technical Motivation:
Pervasive context-aware computing technologies are essential enablers for next generation applications for the digital workplace, consumer electronics, research, education, government and health-care. These enhanced technologies are expected to be in the mainstream in the next 5-10 years. Context-aware cognitive support requires activity and context information to be captured and, ever more often, moved across devices – securely, efficiently and with multi-device interoperability.
Task- and activity-based computing originated in the HCI/CSCW community, where researchers present their work at the ACM-SIGCHI/CSCW conferences and similar forums. Recently, much work in context modeling, human activity recognition/modeling using machine learning techniques and sensor input has been presented in the AI and machine learning community. As such, activity-based computing lies in the intersection of these two communities. In addition, context representation has received a lot of attention in the information technology community and among mobile software vendors. This workshop intends to lay the groundwork for techniques to represent activity context using a synthesis of these approaches to reduce demands on people, such as the cognitive load inherent in activity/context switching, and enhancing human and device performance.
Main Objectives: The intended end results of the workshop are:
- Develop two-three key themes for research with specific opportunities for collaborative work in the next five years in this academically and commercially important area, with topics including, but not limited to human-computer interaction/CSCW, semantic computing, task modeling, context representation, and activity recognition.
- Create a core research group forming an international academic and industrial consortium to significantly augment existing standards/drafts/proposals and create fresh initiatives to enable capture, transfer, and recall of activity context across multiple devices and platforms used by people individually and collectively.
- Review/revise an initial draft of structure of potential Activity Context Representation and Exchange Language (ACEL) which will be made into a draft Request for Comments (RFC) by the industry consortium by January 2012. This will include identification of use cases, list of domain-specific instantiations needed along with owners and draft of initial reasoning schemes and algorithms.
Topics and Research Questions to be Explored
This workshop will explore task and context modeling issues of capture, representation, exchange, standardization and interoperability for creating context-aware and activity-based assistive cognition tools. The discussion at the workshop will focus on the following topics and their corollaries.
Activity Modeling and Representation: Which (low-level) human activities can be reliably learned and detected? How indicative are those for human tasks and intent? Which granularities of activities could be chosen for creating an extensible hierarchy of human activity? What types of, and to what extent, context information can be captured and incorporated in activity models? What are the most effective and efficient methods for incorporating context information in activity models?
Context Representation within Activities: What machine languages are most suitable for activity representation to enable activity and context switching and context recall across devices, platforms and technologies? Do we need user-device specific activity and context dialogue sub-languages?
Semantic Activity Reasoning: How to model and represent activities, objects, resources, actions and their semantics in their context during task performance? How do we design activity/context models to enable the searching of repositories of previous activities that have behaviorally and semantically similar components to current activity requirements?
Security and Privacy: What features must be designed into activity /context models for information exchange across enterprise or private domain boundaries to enable masking, security and privacy measures without compromising user experience?
Information integration and exchange: How can we integrate and exploit the growing amount of information available from devices, services, the environment and general background knowledge to support activity context recognition tasks? What common ontologies or data vocabularies will be useful? What language and formalisms are suitable to enable exchange of this information across devices?
Context Capture: How far can the context capture be automatic and to what extent will it require collaborative meta-dialogue between people and devices? What might be ways of determining the most relevant elements of context for a given task and for an activity/context switch?
For instance, within an activity there may be context elements such as the following (these are merely suggestions to seed discussions and need to be augmented by research at the workshop and subsequently):
User: Users work within a role, permissions, preferences, bringing past and immediate history, memory, skills, goals and perceptions.
Type of Activity and Domain: People create diverse activities in multiple domains, including but not limited to office work, healthcare, education, and entertainment.
Social: Users have the support of collaborators, connected devices and adjacent networks.
Spatial and Temporal: People may be at a certain geo-location, experiencing local conditions (weather, traffic, network connectivity). Tasks may be synchronous or asynchronous.
Resources Available: Users may have access to other people, databases, multiple applications, networks, related datasets, transportation methods, non-electronic resources (tools, paper etc.).
Devices and Interfaces: People may work on a variety of devices such as laptops, desktops, netbooks, tablets, cell phones, using multiple applications, operating systems and interfaces.
Format of workshop
This two day workshop (August 7th-8th, 2011) will include keynotes to set the tone, comprehensive reviews of the field, new proposals, panel focusing on key research issues and directions, presentations on new frameworks for synthesis of multiple/new approaches, poster presentations and working groups to investigate sub-areas. The workshop will conclude with the formation of an international consortium. There will be plenty of opportunity for questioning existing systems, creating research partnerships and identifying fresh research ideas.
The size of the workshop will be 25-35 researchers with about 15 invited participants and about 15 participants selected from the respondents to the call for participation. There may be 3-4 observers from among technical leaders in industry and 1-2 research analysts from Gartner/Forrester who might want to maintain awareness of the current status in the field.
Submission requirements: Researchers should submit 6 page papers or 3-4 page position statements in the standard AAAI format. Researchers wanting to participate without submitting a paper or position statement should provide a 1-2 page statement of interest along with a description of their related work and publications. All the selected papers will be published in a AAAI Technical Report volume.
Submission: Please email all submissions, statements, or requests to be on this workshop’s (moderated) mailing list to Vikas Agrawal (activitycontext@infosys.com).
Important Dates:
- May 8th, 2011: Papers and proposals due to activitycontext@infosys.com (PDF or Microsoft Word) – Please contact us if you need an extension and we will work with you to make the best workshop program.
- May 13th, 2011: List of participants sent to AAAI.
- May 16th, 2011: Reviewer requests for modification shared with authors.
- May 20th, 2011: Notification sent to authors about the type of presentation expected at the workshop.
- May 27th, 2011: Final workshop papers due at AAAI along with AAAI’s Distribution License Form.
- August 7th and 8th, 2011: Workshop in San Francisco
Authors of all accepted or invited workshop papers will need to sign AAAI’s Distribution License form and mail or FAX it to AAAI by 27 May 2011: Association for the Advancement of Artificial Intelligence, 445 Burgess Drive, Suite 100, Menlo Park, California 94025, USA, (650) 321-4457 (FAX)
Workshop Contact: All communications should be addressed to Vikas Agrawal (activitycontext@infosys.com)
Phone: +91-40-4429-4074 Voicemail: +1-916-458-0484
Workshop Organizing Committee
Lokendra Shastri (Chair), Associate Vice President and Head of Research, Software Engineering and Technology Labs, Infosys Technologies Limited, India. Email: lokendra_shastri@infosys.com; Phone: +91-80-4116-4232.
James “Bo” Begole, Principal Scientist and Manager, Ubiquitous Computing, Palo Alto Research Center (PARC), Palo Alto, CA.
Tim Finin, Professor, Computer Science and Electrical Engineering, University of Maryland, Baltimore MD.
Henry Kautz, Chair and Professor, Department of Computer Science, University of Rochester, Rochester, NY.
Matthai Philipose, Senior Researcher, Intel Research Labs, Intel Corporation, Seattle, WA.
Workshop Program Committee
Jakob E. Bardram, Professor, IT University of Copenhagen, Denmark. ACM UbiComp 2010 Co-Chair, ACM CSCW 2011 Papers and Notes Co-Chair (Review Panel)
Oliver Brdiczka, Chief Scientist at Meshin, and Research Scientist, Ubiquitous Computing, Palo Alto Research Center (PARC)
Dan Diaper DDD SYSTEMS, U.K (Review Panel)
Arijit Laha, Senior Research Scientist, Center for Knowledge Driven Information Systems, Infosys Technologies Limited, India. (Review Panel)
Ora Lassila, Member of Nokia CEO Technology Council & Principal Technologist, Nokia Mobile Solutions
Sanjiv Nanda, Senior Director, Corporate Research and Development, QualComm
Philippe Palanque, Professor and Head of Interactive Critical Systems at IRIT, ACM SIG-CHI Adjunct Chair for Specialized Conferences (2007-13)
Kurt Partridge, Research Scientist at PARC
Munindar P. Singh, Professor, North Carolina State University, Raleigh NC USA.
Desney Tan, Senior Researcher and Manager, Microsoft Research, Computational User Experiences Group, Redmond, WA (General Chair, ACM-SIGCHI on Human Factors in Computing Systems 2011) (Review Panel)
Gerrit van der Veer (President, ACM SIG-CHI) Professor, Open University Netherlands (OUN) (Review Panel)
Evelyne Viegas, Director, Semantic Computing, Microsoft Research, Redmond, WA.
Yingxu Wang, Professor of Software Engineering and Cognitive Informatics, Department of Electrical and Computer Engineering, University of Calgary, Canada
Benefits: Many major benefits are anticipated, for example, seamless context switching across devices and tasks and the ability to record, reuse and enable sophisticated work such as semantic activity reasoning, search and decision making in complex personal and group environments that might depend on understanding cognitive, social and institutional knowledge, predicting the actions of actors such as consumers, co-workers, etc., and of the behavior of personal and other people’s technologies.
This workshop is expected to spur significant cooperative research and development of pervasive computing applications in domains as diverse as retail marketing, entertainment, healthcare, life sciences, biotechnology, and product design by working towards creating a common language for interchange of activity context. Additional benefits are expected to include technology for creating application add-ins for context capture and task flow capture to enable investments in legacy applications to be used along with next generation technologies.
