"image-caption pairs" Papers
2 papers found
Conference
Locality Alignment Improves Vision-Language Models
Ian Covert, Tony Sun, James Y Zou et al.
ICLR 2025arXiv:2410.11087
11
citations
Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
Yuanmin Tang, Jing Yu, Keke Gai et al.
CVPR 2025arXiv:2503.17109
15
citations