GLIP: Grounded Language-Image Pre-training
Unifying object detection and phrase grounding enables transferable, open-vocabulary visual recognition.
BibTeX citation
@inproceedings{glip2022,
title = {GLIP: Grounded Language-Image Pre-training},
author = {Liunian Harold Li and Pengchuan Zhang and Haotian Zhang and Jianwei Yang and Chunyuan Li and Yiwu Zhong and Lijuan Wang and Lu Yuan and Lei Zhang and Jenq-Neng Hwang and Kai-Wei Chang and Jianfeng Gao},
booktitle = {CVPR},
year = {2022},
url = {https://arxiv.org/abs/2112.03857}
}