|
|
|||||||||||||||||||||
|
Home | Organization | Registration | ICMI 2007 | Schedule | Abstracts |
|||||||||||||||||||||
1st International WorkshopTagging, Mining and Retrieval of Human-Related Activity InformationThursday 15th November 2007Nagoya Marunouchi Tokyu
Inn Venue
The workshop session will be held at the Nagoya
Marunouchi Tokyu Inn,
located in front of the Marunouchi subway station.
(Use exit #3) |
|||||||||||||||||||||
Important Dates
The schedule of presentations is now viewable
online, along with the paper abstracts.
Workshop FormatWe hope to bring together researchers from multiple disciplines, in areas related to information retrieval, content-analysis, and HCI. The workshop will consist of a mixture of long and short presentations and demonstrations of novel applications and new technologies. Short papers (2 to 4 pages) and long papers (up to 8 pages) will be considered. Submissions should conform to the ACM publication format described at http://www.acm.org/sigs/pubs/proceed/template.html. Please submit papers in PDF format to both workshop organizers:
Accepted papers will be included in the ACM Digital Library. Further opportunities for publication of the best papers will be discussed during the workshop. Rationale and AimsInexpensive and user friendly cameras, microphones, and other devices such as digital pens are making it increasingly easy to capture, store and process large amounts of data over a variety of media. This opportunity has been embraced by a large number of people, and resulted in the availability of high volumes of digital photos, videos, audio recordings. Additional opportunities present themselves for capture of even richer data, for example during lectures, meetings, or informal gatherings. Even though the barriers for data acquisition have been lowered, making use of these data remains challenging. Effective use presupposes a large investment in manual organization, e.g. by careful, labor-intensive labeling of data, manual clustering (e.g. via foldering), or manual extraction and transcription of important information. As a result of the difficulties involved in finding and reusing information, particularly as the volume grows, large amounts of collected data remains unused and inaccessible. Because of that, the collection efforts tend to be abandoned, or not even implemented, given the low immediate payoff and the high cost of organization. More importantly, information that could lead to enhanced performance during learning or work situations remain untapped. The focus of the present workshop is therefore on issues related to theory, methods and techniques for facilitating the organization, retrieval and reuse of multimodal information. The emphasis is on organization and retrieval of information related to human activity, i.e. that is generated and consumed by individuals and groups as they go about their work, learning and leisure. We invite submissions of position papers as well as technical contributions related to: User interface design and evaluation; Tagging, mining and retrieval techniques; Applications of multimodal retrieval, and Cognitive foundations of organization and search of multimodal materials. Topics of interest include, but are not limited to:
o Collaborative multimodal elicitation of tags; social tagging and social use of multimodal materials; o Automated and semi-automated techniques for tag extraction; o Cross-modal, cross-media annotation; non-textual tags; o Tangible/non-conventional interfaces for organizing, annotating and retrieving multimodal materials; gestural interfaces; o Detection an extraction/mining of complex, multi-faceted items such as action items, decisions from multimodal streams; o Interfaces for retrieval; non-textual retrieval techniques: appearance-based, phonetic, digital ink-based search; relevance feedback; o Automated organization of multimodal materials to facilitate retrieval; presentation issues; summarization; o Context and content-sensitive tagging and retrieval; sensor-, temporal-, and semantic-based tagging and retrieval; o Multi-document annotation; emergent annotation and retrieval processes; o Human issues related to the organization and retrieval of multimodal materials; linguistic and cognitive aspects of multimodal tagging and retrieval; o Multimodal approaches to retrieval of non-conventional data such as music; o Collection and analysis infrastructures; collection methodologies; interfaces for analysts; o Applications in science, education, entertainment; industrial applications. |
|||||||||||||||||||||
|
|