Contrastive Localized Language-Image Pre-Training
Region-text contrastive learning produces visual representations for fine-grained recognition, retrieval, and grounded multimodal understanding.
BibTeX citation
@inproceedings{cloc2025,
title = {Contrastive Localized Language-Image Pre-Training},
author = {Hong-You Chen and Zhengfeng Lai and Haotian Zhang and Xinze Wang and Marcin Eichner and Keen You and Meng Cao and Bowen Zhang and Yinfei Yang and Zhe Gan},
booktitle = {ICML},
year = {2025},
url = {https://arxiv.org/abs/2410.02746}
}