2 papers
cs.CV2024
Learning to Adapt Category Consistent Meta-Feature of CLIP for Few-Shot Classification
Jiaying Shi, Xuetong Xue, Shenghui Xu
The recent CLIP-based methods have shown promising zero-shot and few-shot performance on image classification tasks. Existing approaches such as CoOp and Tip-Adapter only focus on…
cs.CV2024
MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model
Ziqi Ren, Jie Li, Xuetong Xue +4
Deciphering the human visual experience through brain activities captured by fMRI represents a compelling and cutting-edge challenge in the field of neuroscience research. Compared…