Vision-Language Learning | Wenrui Fanhttps://wenruifan.github.io/tags/vision-language-learning/Vision-Language LearningHugoBlox Kit (https://hugoblox.com)en-usFri, 15 Mar 2024 12:00:00 +0000https://wenruifan.github.io/media/icon_hu_75a089107c6a8eba.pngVision-Language Learninghttps://wenruifan.github.io/tags/vision-language-learning/MeDSLIP releasedhttps://wenruifan.github.io/blog/2024-medslip/Fri, 15 Mar 2024 12:00:00 +0000https://wenruifan.github.io/blog/2024-medslip/<p>We released , a dual-stream vision-language pre-training framework for fine-grained medical image-text alignment.</p>MeDSLIP: medical dual-stream language-image pre-training with pathology-anatomy semantic alignmenthttps://wenruifan.github.io/publications/medslip/Fri, 15 Mar 2024 00:00:00 +0000https://wenruifan.github.io/publications/medslip/