FOCAL: Fine-Grained Optimal-Transport-Driven Contrastive Alignment of Language and ECGs with Waveform Enhancement
This paper proposes FOCAL, a novel framework that achieves precise, fine-grained alignment between localized ECG segments and individual report tags via Optimal Transport, and introduces a semantic similarity matrix to guide the contrastive objective and correct misalignments.
Hai-Tao Li, Che Liu, Zheng-Yao Ding et al.
· 2 citations