datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
GazeVaLMFull paper can be found here.
GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays
This is the official dataset repository for the paper GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays.
GazeVaLM is a public eye-tracking dataset for studying clinical perception during chest radiograph authenticity assessment. The dataset comprises 960 gaze recordings from 16 expert… See the full description on the dataset page: https://huggingface.co/datasets/davidcwong/GazeVaLM.GazeSearch
GazeSearch: Radiology Findings Search Benchmark (WACV 2025)
Access is gated. This dataset contains images derived from
MIMIC-CXR and is only shared with users credentialed under the
PhysioNet Credentialed Health Data Use Agreement. Click Request
access at the top of the page and confirm you hold an active
MIMIC-CXR credentialed-access account; requests without proof of
authorization will be denied.
GazeSearch is a curated visual search dataset for evaluating search
algorithms on… See the full description on the dataset page: https://huggingface.co/datasets/phamtrongthang/GazeSearch.