VeCLIP: Improving CLIP Training via Visual-enriched Captions
Visual-enriched caption rewriting improves image–text alignment and the data efficiency of CLIP pre-training.
BibTeX citation
@inproceedings{cliptraining2024,
title = {VeCLIP: Improving CLIP Training via Visual-enriched Captions},
author = {Zhengfeng Lai and Haotian Zhang and Bowen Zhang and Wentao Wu and Haoping Bai and Aleksei Timofeev and Xianzhi Du and Zhe Gan and Jiulong Shan and Chen-Nee Chuah and Yinfei Yang and Meng Cao},
booktitle = {ECCV},
year = {2024},
url = {https://arxiv.org/abs/2310.07699}
}