AGREE: Aligning Cross-Modal Entities for Image-Text Retrieval Upon Vision-Language Pre-trained Models.

@inproceedings{wang-2023-agree, author = {Xiaodan Wang and Lei Li and Zhixu Li and Xuwu Wang and Xiangru Zhu and Chengyu Wang and Jun Huang and Yanghua Xiao}, editor = {Tat-Seng Chua and Hady Wirawan Lauw and Luo Si and Evimaria Terzi and Panayiotis Tsaparas}, title = {{AGREE: Aligning Cross-Modal Entities for Image-Text Retrieval Upon Vision-Language Pre-trained Models}}, booktitle = {{Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, WSDM 2023, Singapore, 27 February 2023 - 3 March 2023}}, pages = {456--464}, publisher = {ACM}, year = {2023}, url = {https://doi.org/10.1145/3539597.3570481}, doi = {https://doi.org/10.1145/3539597.3570481} }