Tao-Wei Li

Multi-Granularity Text and Scale-Aware Visual Encoding for Remote Sensing Image-Text Retrieval and Prompt-Based Scene Recognition

A CLIP-style dual encoder with three targeted additions that preserves word-level, phrase-level, and sentence-level representations before fusing them through cross-granularity attention, and a semantic membership-aware contrastive loss that applies detached, bounded discount weights to semantically close negatives wit...