VQA-Med: Overview of the Medical Visual Question Answering Task at ImageCLEF 2019

By Asma Ben Abacha, Sadid A. Hasan, Vivek Datla, Joey Liu, Dina Demner-Fushman, Henning Müller. 2019

322 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Maryam Rahnemoonfar
2. Xiaoman Zhang
3. Pengtao Xie
4. Tashnim Chowdhury
5. Eric P. Xing
6. Weidi Xie
7. Chaoyi Wu
8. Argho Sarkar

Citations in the corpus

• FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding (2020, methodology): “VQA-MED [2] Medical Images No No Varies in size 7 7 X”
• PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering (2023, background): “Potential Annotation Biases: Despite efforts to ensure quality and accuracy during the annotation process of PMC-VQA-test-clean, the dataset may still be susceptible to annotation biases.”
• PathVQA: 30000+ Questions for Medical Visual Question Answering (2020, background): “The VQA-Med [6] dataset is created on 4,200 radiology images and has 15,292 question-answer pairs.”
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling (2024, unknown): “…(en & zh) PMC-VQA (en) [303], VQA-RAD (en) [120], ImageCLEF (en) [72], PMC (en) [261], SLAKE (en & zh) [145], GMAI-VL (en & zh) [134], VQA-Med (en) [15], Medical-Diff-VQA (en) [94], PathVQA (en) [83], Medical PMC-CaseReport (en) [260] Screen2Words (en) [240], WebSight (en) [122], Widget-Caption…”