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. An important change from previous years is that all Grand Challenge participants will give a poster/demo presentation during the main portion of the conference. Additionally, all Grand Challenge papers will be evaluated by ICMI participants in order to determine the recipient(s) of the overall Best Grand Challenge Paper Award.
We are seeking organizers to propose and run Grand Challenge events. Both academic and corporate organizers are welcome. We are looking for up to three types of challenges in any of the following categories:
- 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.
- Design Challenges. This challenge will include the creation of physical and/or virtual applications, presumably around a given theme. As with the aforementioned challenges, proposers should clearly describe how the design challenge submissions will be evaluated, and what level of fidelity will be required of design submissions.
We are also soliciting proposals that align with the theme of the conference, Multimodal interaction on mobile/wearable devices & large displays, as described below:
- Mobile interaction challenge. This challenge will include the description of a task that is currently performed on mobile devices and will elicit contributions of systems or apps that improve the human performance of the task (e.g. improve multimodal text entry on smartwatches by 20%). The challenge proposal must specify the task and the metric, methodology, and resources used to evaluate the performance improvements.
- Multimodal Interaction with large displays challenge. This type of challenge will include using state-of-the-art technology and techniques and improve one or more aspects of how people interact with large screen displays. In particular in may involve improving multimodal input for a specific application, or more broadly address the integration of custom technology to extend multimodal large screen display interaction to include a novel set of modalities.
Prospective organizers should submit a five-page maximum proposal containing the following information:
- Title
- Abstract appropriate for possible Web promotion of the Challenge
- Detailed description of the challenge and its relevance to multimodal interaction
- Plan for soliciting participation, including research communities that you will distribute your solicitation to
- Description of how submission will be evaluated and proposed reviewers
- Proposed schedule for releasing datasets (if applicable) and receiving submissions
- Short biography 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.
Important Dates and Contact Details
Proposals should be emailed to any of the ICMI 2015 Multimodal Grand Challenge Chairs, Dr. Cosmin Munteanu (cosmin@taglab.ca) and Dr. Marcelo Worsley (mworsley@ict.usc.edu). Prospective organizers are also encouraged to contact the co-chairs if they have any questions. Continuation of or variants on the 2014 challenges are welcome, though we ask for submissions of this form to highlight the number of participants that attended during the previous year and describe what changes will be made from the previous year. Proposals are due by February 21st, 2015. Notifications will be sent on March 1st, 2015
Download