GilBERT: Generative Vision-Language Pre-Training for Image-Text Retrieval.

@inproceedings{hong-2021-gilbert, author = {Weixiang Hong and Kaixiang Ji and Jiajia Liu and Jian Wang and Jingdong Chen and Wei Chu}, editor = {Fernando Diaz and Chirag Shah and Torsten Suel and Pablo Castells and Rosie Jones and Tetsuya Sakai}, title = {{GilBERT: Generative Vision-Language Pre-Training for Image-Text Retrieval}}, booktitle = {{SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021}}, pages = {1379--1388}, publisher = {ACM}, year = {2021}, url = {https://doi.org/10.1145/3404835.3462838}, doi = {https://doi.org/10.1145/3404835.3462838} }