Feeding a model-generated radiology report as additional context improves chest X-ray visual question answering, setting a new state of the art on the Medical-Diff-VQA benchmark.
Pretraining Vision- Language Model for Difference Visual Question An- swering in Longitudinal Chest X-rays
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports
Feeding a model-generated radiology report as additional context improves chest X-ray visual question answering, setting a new state of the art on the Medical-Diff-VQA benchmark.