Overview of the VQA-Med task at ImageCLEF 2021 : visual question answering and generation in the medical domain
Ben Abacha, Asma; Sarrouti, Mourad; Demner-Fushman, Dina; Hasan, Sadid A.; Müller, Henning
2021

Résumé

This paper presents an overview of the fourth edition of the Medical Visual Question Answering (VQA-Med) task at ImageCLEF 2021. VQA-Med 2021 includes a task on Visual Question Answering (VQA),where participants are tasked with answering questions from the visual content of radiology images,and a second task on Visual Question Generation (VQG), consisting of generating relevant questionsabout radiology images. Thirteen teams participated in VQA-Med 2021 and submitted a total of 75 runs.The best teams achieved a BLEU score of 0.416 in the VQA task and 0.383 in the VQG task.

Détails

Titre Overview of the VQA-Med task at ImageCLEF 2021 : visual question answering and generation in the medical domain
Auteur(s)/ trice(s) Ben Abacha, Asma (National Library of Medicine, USA)
Sarrouti, Mourad (National Library of Medicine, USA)
Demner-Fushman, Dina (National Library of Medicine, USA)
Hasan, Sadid A. (CVS Health, USA)
Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis))
Date 2021-09
Publié dans Proceedings of the CLEF 2021 Conference and Labs of the Evaluation Forum - working notes
Editeur Bucharest, Romania, 21-24 September 2021
Pagination Pp. 1081-1088
Présenté à CLEF 2021 Conference and Labs of the Evaluation Forum, Online, 2021-09-21, 2021-09-24
ISSN 1613-0073
Mots-clés (libres) visual question answering ; visual question generation ; data creation ; radiology images
Type de papier published full paper
Domaine Economie et Services
Ecole HEG-VS
Institut Institut Informatique de gestion
Le document apparaît dans Documents de conférences
Global
Ressource(s) externe(s) Online version

Actions

PDF