CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels 论文

2023Proceedings of the AAAI Conference on Artificial Intelligence引用 231
DOIPDF
Multimodal Machine Learning ApplicationsCOVID-19 diagnosis using AIImage Retrieval and Classification Techniques
人工智能Multimodal Machine Learning ApplicationsImage Retrieval and Classification TechniquesCOVID-19 diagnosis using AI
相关技术:Image Retrieval and Classification TechniquesMultimodal Machine Learning Applications
关系图谱

CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels · 作者

S

Siyuan Li

Q

Qingli Li

S

Sun Li