CFP: Activity Context Representation: Techniques and Languages. Two Day
Workshop at AAAI '12 (July 22-23, Toronto).
April 9th, 2012: Papers/proposals due to organizers
Organizers: Lokendra Shastri (Infosys), Henry Kautz (Rochester); James “Bo” Begole (Samsung - User Experience), Tim Finin (University of Maryland, Baltimore), Munindar P. Singh (NCSU, Raleigh)
Description: Pervasive context-aware computing technologies are essential enablers for next generation applications for the digital workplace, consumer electronics, research, education, government and health-care. 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.
In this workshop we will explore task and context modeling issues of capture, representation, exchange, standardization and interoperability for creating context-aware and activity-based assistive cognition tools, including but not limited to the following (details available at
*Activity Modeling, Representation, Recognition, Detection, and Acquisition *Context Capture and Representation within Activities
*Semantic Activity Reasoning and Guidance
*Information integration and Exchange
*Use-cases/Scenarios, Architectures and Prerequisites
*Security and Privacy
The objectives and intended end results of the workshop are (please see details at http://activitycontext.org/about/intended-outcomes/):
1. Discuss and review/revise initial drafts of structure of potential Activity Context Representation and Exchange Languages
2. Explore fresh topics by discussing position papers/proposals building on key research focus areas.
3. Create and strengthen a core research group, identify new collaborations, and formalize an international academic and industrial consortium to significantly augment existing standards/drafts/proposals and create new research initiatives.
Format of workshop: This two day workshop will include keynotes to set the tone, invited comprehensive reviews of the field, new proposals, open panel focusing on key research issues and directions, discussion of proposals on new frameworks for synthesis of multiple/new approaches, and working group formation to investigate sub-areas during the year. 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 25-30 researchers with about 12 invited participants and about 12 participants selected from the respondents to the call for participation. There may be 1-2 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.
Those wanting to participate without submitting a 6 page paper or 4 page position statement, will need to provide a 1-2 page statement of interest along with a description of their related work.
All accepted papers/proposals will be included in a formal AAAI '12 Technical Report. Here is an example from the last year's workshop: http://aaai.org/ocs/index.php/WS/AAAIW11/schedConf/presentations
*April 9th, 2012: Workshop submissions due to organizers
*April 20th, 2012: Notifications sent to authors
*April 20th, 2012: List of participants due at AAAI
*May 16th, 2012: Final workshop papers due at AAAI
1. Papers/proposals will normally be 6-8 pages in length, and be in PDF format. We also welcome short (maximum 3-4 pages) submissions with detailed design or representation technology/language proposals at a concept stage, relevant to the workshop focus. Multiple submissions from the same authors will be accepted on a case by case basis.
2. We request a 1-2 page Statement of Interest from anyone who wishes to attend without submitting a paper. In this statement, please describe your relevant interest, related projects (if any), and list a few relevant publications (if any).
3. Please email all submissions, or requests to be on this workshop’s (moderated) mailing list to Vikas Agrawal ([log in to unmask])
4. The Workshop Organizing Committee will select presentations through a peer review process.
5. PDF paper/proposal submissions should be formatted according to the AAAI 2012 Workshop Author Instructions, with the addition of your name(s), affiliation(s), and email address(es) at the top of the first page as this will not be a double-blind reviewing process.
6. Authors of all accepted or invited workshop papers should sign AAAI’s Distribution License form and mail or FAX it to AAAI:
Association for the Advancement of Artificial Intelligence
445 Burgess Drive, Suite 100
Menlo Park, California 94025, USA
Research Questions to be Explored
We 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 will focus on the following topics and their corollaries:
1. Activity Modeling, Representation, Recognition, Detection, and Acquisition: 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?
2. 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?
3. 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?
4. 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?
5. 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 exchange techniques and formalisms will be most effective in specific domains? How can the externalized cognitive state transfer be properly affected?
6. What are the relevant use-case scenarios and collaboration environments? What are suitable software architectures, user interfaces, developer tools, benchmarking tools for activity-based computing? What kind of text, context and behavioral analytics is needed?
7. 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):
a. User: Users work within a role, permissions, preferences, bringing past and immediate history, memory, skills, goals and perceptions.
b. Type of Activity and Domain: People create diverse activities in multiple domains, including but not limited to office work, healthcare, education, and entertainment.
c. Social: Users have the support of collaborators, connected devices and adjacent networks.
d. Spatial and Temporal: People may be at a certain geo-location, experiencing local conditions (weather, traffic, network connectivity). Tasks may be synchronous or asynchronous.
e. Resources Available: Users may have access to other people, databases, multiple applications, networks, related datasets, transportation methods, non-electronic resources (tools, paper etc.).
f. 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.
Task- and activity-based computing originated in the HCI/CSCW community, such as the ACM-SIGCHI/CSCW conferences. 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. Context representation has received a lot of attention in the information technology community and in the industry among mobile vendors. As computers have become more powerful, the tools from AI and applications in HCI have come much closer.
This second international workshop on Activity Context Representation is expected to build on the groundwork laid at the first workshop at AAAI’11, for establishing an international academic and industrial consortium for developing systems that capture, transfer, and recall activity context across multiple devices and platforms used by people individually and collectively. The workshop will explore 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/device switching and enhance human performance within activities.
The scope of the workshop includes finding techniques for creating context, activity-driven systems providing end-user value through monitoring, exchange and support on activities which can be performed better with help of computational devices than otherwise. The consortium and workshop interest is focused on using AI techniques to improve the human-computer interface for better human performance of knowledge work. Therefore, applications in machine-to-machine systems (manufacturing, smart grid, load balancing), standard data mining and web-based behavioral analytics are kept out of scope.
This workshop will create a strong collaborative team of AI and HCI researchers to deliver the techniques and solutions needed for context-aware computing systems that reduce cognitive load on users by providing an intelligent interface and toolset for knowledge workers. This focused team will work with industry and academia to create fast moving domain-specific standards for application and device context transfer via peer-to-peer and services in the Cloud. The community will remain engaged via the website, ongoing standard and techniques creation activities and research focus-groups. The international consortium will serve as the forum for research funding and engaging industry.
The workshop expects to make serious progress in key research areas identified at the AAAI’11 workshop for longer term focus:
1. User/Intent Modeling, Activity Recognition, Detection, Acquisition, Observation, Recording Tacit Knowledge and Cognitive State Transfer
2. Activity Context Analysis, Modeling, Representation, and Ontologies
3. Developing Use Cases/Scenarios, Defining User Interfaces, Identifying Collaboration Tools, Software Architectures, Developer Tools, Benchmarking Tools for Activity Based
4. Text, Context and Behavioral Analytics
5. Security and Privacy
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, product design and pervasive computing experience providers by creating a common language for interchange of activity context, task / activity model representations and context representations for assistive cognition devices, the digital workplace and the consumer play-space. Major benefits include seamless context switching across devices / tasks and ability to record, reuse and enable semantic task reasoning / search, learning from and guiding user actions. Side benefits made may 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.
**************** CAUTION - Disclaimer *****************
This e-mail contains PRIVILEGED AND CONFIDENTIAL INFORMATION intended solely
for the use of the addressee(s). If you are not the intended recipient, please
notify the sender by e-mail and delete the original message. Further, you are not
to copy, disclose, or distribute this e-mail or its contents to any other person and
any such actions are unlawful. This e-mail may contain viruses. Infosys has taken
every reasonable precaution to minimize this risk, but is not liable for any damage
you may sustain as a result of any virus in this e-mail. You should carry out your
own virus checks before opening the e-mail or attachment. Infosys reserves the
right to monitor and review the content of all messages sent to or from this e-mail
address. Messages sent to or from this e-mail address may be stored on the
Infosys e-mail system.
***INFOSYS******** End of Disclaimer ********INFOSYS***
To unsubscribe, send an empty email to
mailto:[log in to unmask]
For further details of CHI lists see http://listserv.acm.org