Request to add ICCV2025: Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching

[liuyyy111]

Paper title: Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching
Paper link: https://arxiv.org/pdf/2503.14953
Code link: https://github.com/liuyyy111/d2s-vse
Project link: https://d2s-vse.github.io/