A video-based eye-gaze prompt improved report generation and diagnosis for one general-purpose vision-language model, LLaVA-OneVision, but hurt or barely helped two others, and the main comparison to medical models rests on a questionable metric.
In: Findings of the Association for Computational Linguistics ACL 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
RadEyeVideo: Enhancing general-domain Large Vision Language Model for chest X-ray analysis with video representations of eye gaze
A video-based eye-gaze prompt improved report generation and diagnosis for one general-purpose vision-language model, LLaVA-OneVision, but hurt or barely helped two others, and the main comparison to medical models rests on a questionable metric.