Return
Text-guided camouflaged object detection
DOI:10.1016/j.patcog.2025.112058.png)
Abstract
En 中文
• In-context learning-based method to extract valuable textual information for camouflaged targets from MLLMs. • TG-COD framework integrate textual semantic guidance in both the learning and inference processes. • TG-COD demonstrates SOTA performance and exhibits superior generalization capability.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available

