posted by organizer: ICMIEAT || 2038 views || tracked by 3 users: [display]

ICMI EAT 2018 : ICMI Audio/Visual Eating Analysis & Tracking Challenge


When Oct 20, 2018 - Oct 20, 2018
Where Boulder, CO, USA
Submission Deadline May 30, 2018
Notification Due Jul 18, 2018
Final Version Due Jul 31, 2018
Categories    multimodal interaction   machine learning   computational paralinguistics

Call For Papers

We are calling for participation in ICMI EAT, the 1st Audio/Visual Eating Analysis & Tracking Challenge, held as a session of ACM International Conference on Multimodal Interaction 2018 in Boulder, CO, USA on 20th October 2018.

The Audio/Visual Eating Analysis & Tracking Challenge (ICMI EAT 2018) will be the first audio-visual open research competition under strictly comparable conditions dealing with Machine Learning for audio/visual tracking of human subjects’ recorded while eating different types of food during speaking.

The Challenge will focus on multimodal recognition of eating conditions:
1) whether a person is eating or not - and if yes, which food type
2) recognizing the subjects' food likability rating
3) recognizing the level of difficulty to speak while eating

For more information, see

ICMI EAT shall help bridging the gap between current-state research on multimodal machine learning, computational paralinguistics, and user behaviour tracking.

All Sub-Challenges allow participants to find their own acoustic/visual features and/or their own machine learning model. Standard acoustic and visual feature sets will be provided featuring recent end-to-end deep learning and more ground-breaking crossmodal bag-of-words that may be used by the participants. We encourage both contributions aiming at highest performance, and contributions aiming at fostering brave new ideas in this context.

In order to participate in the Challenge, please register your team by following the challenge guidelines.

Besides participation in the Challenge we are calling for papers addressing the overall topics of this session, in particular works that address the differences between audio and video of eating condition data, and the issues concerning combined audio-visual eating recognition.

Important Dates

Release of training data and evaluation script:
4 April 2018
Release of test data:
16 May 2018
Paper submission:
30 May 2018
Notification of acceptance:
18 July 2018
Camera ready paper:
31 July 2018
20 October 2018

Related Resources

ICMI 2021   International Conference on Multimodal Interfaces
WSDM 2022   Web Search and Data Mining
AIKE 2021   IEEE Artificial Intelligence & Knowledge Engineering 2021
ACML 2021   The 13th Asian Conference on Machine Learning
XSA 2021   Explainable Deep Learning for Sentiment Analysis
IJAD 2021   International Journal of Advanced Dermatology
MDPI-SI-BDHA 2021   Call for Papers: Special Issue “Big Data for eHealth Applications” (MDPI Applied Sciences, IF 2.474 – Indexed on Scopus, Web of Science)
MECHATROJ 2021   Mechatronics and Applications: An International Journal (MECHATROJ)
TERA - Eurasia Research 2021   19th ICTEL 2021 – International Conference on Teaching, Education & Learning, 11-12 October, Lisbon
ICBELLP - Eurasia Research 2021   2021 – XIXth International Conference on Business, Education, Law, Language & Psychology (ICBELLP), 29-30 October, Abu Dhabi