Eye-gazeGuidedMulti-modalAlignmentforMedical RepresentationLearning

Neural Information Processing Systems 

This data-reliance may lead to low generalization of the learned alignment relationships. Inthis work, we propose theEye-gazeGuided Multi-modalAlignment (EGMA) frameworktoharness eye-gazedataforbetter alignment of medical visual and textual features.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found