Call for Multimodal Grand Challenges 2014
The International Conference on Multimodal Interaction (ICMI) is the premier international forum for multidisciplinary research on multimodal human-human and human-computer interaction, interfaces, and system development. Developing systems that can robustly understand human-human communication or respond to human input requires identifying the best algorithms and their failure modes. In fields such as computer vision, speech recognition, and computational linguistics for example, the availability of datasets and common tasks have led to great progress. We invite the ICMI community to collectively define and tackle the scientific Grand Challenges in our domain for the next 5 years. Multimodal Grand Challenges are driven by ideas that are bold, innovative, and inclusive. They should inspire new ideas in the ICMI community and create momentum for future collaborative work. Analysis, synthesis, and interactive tasks are all possible.
We are seeking organizers to propose and run Grand Challenge events. Both academic and corporate organizers are welcome. We are looking for three types of challenges:
Dataset-driven challenge. This challenge will provide a dataset that is exemplary of the complexities of current and future multimodal problems, and one or more multimodal tasks whose performance can be objectively measured. Participants in the Challenge will evaluate their methods against the challenge data in order to identify areas of strengths and weakness.
User case challenge. This challenge will provide an interactive problem/system (e.g. dialog-based) and the associated resources, which can allow people to participate through the integration of specific modules or alternative full systems. Proposers should also establish systematic evaluation procedures.
Concept challenge. This challenge proposes new ideas (e.g. involving new sensors) that, while not fully tested now, could lead to breakthroughs if our community decided to tackle them together or individually.
Prospective organizers should submit a five-page maximum proposal containing the following information:
Abstract appropriate for possible Web promotion of the Challenge
Detailed description of the challenge and its relevance to multimodal interaction
Plan for soliciting participation
Proposed schedule for releasing datasets and receiving submissions
Short bio of the organizers
Funding source (if any) that supports or could support the challenge organization.
Preference (if any) for special session or workshop format.
Proposals will be evaluated based on originality, ambition, feasibility, and implementation plan. The ICMI organizers will offer support with basic logistics.