2026
A Structured, Tagged, and Localized Visual Question Answering Dataset with Full Sentence Answers and Scene Graphs for Chest X-ray Images
ICLR 2026poster
Visual Question Answering (VQA) enables targeted and context-dependent analysis of medical images, such as chest X-rays (CXRs). However, existing VQA datasets for CXRs are typically constrained by simplistic and brief answer formats, lacking localization annotations (e.g., bounding boxes) and struct…