Dear colleagues and friends,

This year, we are organizing the MedVidQA challenge with TRECVID 2023. This challenge aims at developing models for (1) retrieving the relevant videos and locating the visual answer in those videos for the medical or health-related question and (2) generating the medical instructional questions from the video segments. Following the success of the 1st MedVidQA shared task, MedVidQA at TRECVID 2023 expanded the tasks and introduced a new track considering language-video understanding and generation. This track is comprised of two main tasks Video Corpus Visual Answer Localization (VCVAL) and Medical Instructional Question Generation (MIQG). 

For more details, please visit the challenge website (https://medvidqa.github.io/) and TRECVID 2023 website (https://www-nlpir.nist.gov/projects/tv2023/index.html).

The link for submission:

• Task 1 (VCVAL): https://codalab.lisn.upsaclay.fr/competitions/13445
• Task 2 (MIQG): https://codalab.lisn.upsaclay.fr/competitions/13546

Important Dates

• Release of the training and validation datasets: April 30, 2023
• Release of the video corpus: May 12, 2023
• Release of the test sets: July 14, 2023
• Run submission deadline: August 4, 2023
• Release of the official results: September 29, 2023

We look forward to your participation in MedVidQA at TRECVID 2023.

Join our Google Group for important updates! If you have any questions, ask in our Google Group or email us.

Thank you,

MedVidQA 2023 Organizers