[visionlist] ICMI 2019: Call for Multimodal Grand Challenges

zakia hammal zakia_hammal at yahoo.fr
Thu Jan 3 12:33:32 -05 2019

Apologies for cross-posting

ICMI 2019: Call for Multimodal Grand Challenges

Submission Deadline: January 14, 2019

Call for Multimodal Grand Challenges

Proposals due            January 14, 2019
Proposal notification     February 1, 2019
Paper camera-ready     August 12, 2019

We are calling for teams to propose one or more ICMI Multimodal Grand Challenges.

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, computational (para-) linguistics and physiological signal processing, 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. ICMI Multimodal Grand Challenges aim to inspire new ideas in the ICMI community and create momentum for future collaborative work. Analysis, synthesis, and interactive tasks are all possible. Challenge papers will be indexed in the proceedings of ICMI.

The grand challenge sessions are still to be confirmed. We invite organizers from various fields related to multimodal interaction to propose and run Grand Challenge events. We are looking for exciting and stimulating challenges including but not limited to 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 and compared in rigorous conditions. Participants in the Challenge will evaluate their methods against the challenge data in order to identify areas of strengths and weakness.
    Use-case challenge. This challenge will provide an interactive problem system (e.g. dialog-based or non-verbal-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.
    Health challenge. This challenge will provide a dataset that is exemplary of a health related task, whose analysis, diagnosis, treatment or prevention can be aided by Multimodal Interactions. The challenge should focus on exploring the benefits of multimodal (audio, visual, physiological, etc) solutions for the stated task.
    Policy challenge. Legal, ethical, and privacy issues of Multimodal Interaction systems in the age of AI. The challenge could revolve around opinion papers, panels, discussions, etc.

Prospective organizers should submit a five-page maximum proposal containing the following information:

    Abstract appropriate for possible Web promotion of the Challenge
    Distinctive topics to be addressed and specific goals
    Detailed description of the Challenge and its relevance to multimodal interaction
    Length (full day or half day)
    Plan for soliciting participation
    Description of how submissions (challenge’s submissions and papers) will be evaluated, and a list of proposed reviewers
    Proposed schedule for releasing datasets (if applicable) and/or systems (if applicable) and receiving submissions
    Short biography of the organizers (preferably from multiple institutions)
    Funding source (if any) that supports or could support the challenge organization
    Draft call for papers; affiliations and email address of the organisers; summary of the Grand Challenge; list of potential Technical Program Committee members and their affiliations, important dates

Proposals will be evaluated based on originality, ambition, feasibility, and implementation plan. A Challenge with dataset(s) or system(s) that has had pilot results to ensure its representativity and suitability to the proposed task will be given preference for acceptance; an additional 1 page description must be attached in such case. Continuation of or variants on the 2018 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.

The ICMI organizers will offer support with basic logistics, which includes rooms and equipment to run the Workshop, coffee breaks can be offered if synchronised with the main conference.

Important Dates and Contact Details

Proposals should be emailed to both ICMI 2019 Multimodal Grand Challenge Chairs, Prof Anna Esposito and Dr. Michel Valstar via grandchallenge.ICMI19 at gmail.com. Prospective organizers are also encouraged to contact the co-chairs if they have any questions. Proposals are due by January 14th, 2019. Notifications will be sent on February 1st, 2019.

Best regards,
Social Media Chair ICMI 2019

Zakia Hammal, PhD 
The Robotics Institute, Carnegie Mellon University 


More information about the visionlist mailing list