Pre-trained vision-language models, e.g., CLIP, working with manually
de...
The recently rising markup-to-image generation poses greater challenges ...
Vision-language pre-training (VLP) models have shown vulnerability to
ad...
The composed image retrieval (CIR) task aims to retrieve the desired tar...
Cloth-changing person reidentification (ReID) is a newly emerging resear...
Cloth-changing person reidentification (ReID) is a newly emerging resear...
Session-based recommendation (SBR) has drawn increasingly research atten...
Finding tampered regions in images is a hot research topic in machine
le...