{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T10:44:29Z","timestamp":1782125069665,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Science and Technology Innovation Action Plan","award":["22511104700"],"award-info":[{"award-number":["22511104700"]}]},{"name":"National Natural Science Foundation of China","award":["62072323"],"award-info":[{"award-number":["62072323"]}]},{"name":"Science and Technology Commission of Shanghai Municipality Grant","award":["22511105902"],"award-info":[{"award-number":["22511105902"]}]},{"name":"Alibaba Group","award":["Alibaba Innovative Research Program"],"award-info":[{"award-number":["Alibaba Innovative Research Program"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3539597.3570481","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"456-464","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["AGREE: Aligning Cross-Modal Entities for Image-Text Retrieval Upon Vision-Language Pre-trained Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3721-3494","authenticated-orcid":false,"given":"Xiaodan","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8891-1786","authenticated-orcid":false,"given":"Lei","family":"Li","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2355-288X","authenticated-orcid":false,"given":"Zhixu","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3363-570X","authenticated-orcid":false,"given":"Xuwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7308-3642","authenticated-orcid":false,"given":"Xiangru","family":"Zhu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1010-9678","authenticated-orcid":false,"given":"Chengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7706-7081","authenticated-orcid":false,"given":"Jun","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-9591","authenticated-orcid":false,"given":"Yanghua","family":"Xiao","sequence":"additional","affiliation":[{"name":"Fudan University & Fudan-Aishu Cognitive Intelligence Joint Research Center, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475251"},{"key":"e_1_3_2_2_4_1","first-page":"321","article-title":"Image retrieval with reciprocal and shared nearest neighbors","volume":"2","author":"Delvinioti Agni","year":"2014","unstructured":"Agni Delvinioti, Herv\u00e9 J\u00e9gou, Laurent Amsaleg, and Michael E Houle. 2014. Image retrieval with reciprocal and shared nearest neighbors. In VISAPP, Vol. 2. 321--328.","journal-title":"VISAPP"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_2_6_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_7_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.285"},{"key":"e_1_3_2_2_9_1","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan Zhe","year":"2020","unstructured":"Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, and Jingjing Liu. 2020. Large-scale adversarial training for vision-and-language representation learning. Advances in Neural Information Processing Systems 33 (2020), 6616--6628.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00473"},{"key":"e_1_3_2_2_11_1","volume-title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark.","author":"Gu Jiaxi","year":"2022","unstructured":"Jiaxi Gu, Xiaojun Meng, Guansong Lu, Lu Hou, Minzhe Niu, Xiaodan Liang, Lewei Yao, Runhui Huang, Wei Zhang, Xin Jiang, et al. 2022. Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark. (2022)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"e_1_3_2_2_13_1","volume-title":"Image and sentence matching via semantic concepts and order learning","author":"Huang Yan","year":"2018","unstructured":"Yan Huang, Qi Wu, Wei Wang, and Liang Wang. 2018. Image and sentence matching via semantic concepts and order learning. IEEE transactions on pattern analysis and machine intelligence 42, 3 (2018), 636--650."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"e_1_3_2_2_15_1","volume-title":"International Conference on Machine Learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision- language representation learning with noisy text supervision. In International Conference on Machine Learning. PMLR, 4904--4916."},{"key":"e_1_3_2_2_16_1","volume-title":"Chinese lexical analysis with deep bi-gru-crf network. arXiv preprint arXiv:1807.01882","author":"Jiao Zhenyu","year":"2018","unstructured":"Zhenyu Jiao, Shuqi Sun, and Ke Sun. 2018. Chinese lexical analysis with deep bi-gru-crf network. arXiv preprint arXiv:1807.01882 (2018)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_2_18_1","volume-title":"International Conference on Machine Learning. PMLR, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International Conference on Machine Learning. PMLR, 5583--5594."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 1 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123366"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_22_1","volume-title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval. arXiv preprint arXiv:2203.05465","author":"Lei Jie","year":"2022","unstructured":"Jie Lei, Xinlei Chen, Ning Zhang, Mengjiao Wang, Mohit Bansal, Tamara L Berg, and Licheng Yu. 2022. LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval. arXiv preprint arXiv:2203.05465 (2022)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_2_24_1","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. NeurIPS 34 (2021), 9694--9705.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_2_27_1","volume-title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning. arXiv preprint arXiv:2012.15409","author":"Li Wei","year":"2020","unstructured":"Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, and Haifeng Wang. 2020. UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning. arXiv preprint arXiv:2012.15409 (2020)."},{"key":"e_1_3_2_2_28_1","volume-title":"UNIMO-2: End-to-End Unified Vision-Language Grounded Learning. arXiv preprint arXiv:2203.09067","author":"Li Wei","year":"2022","unstructured":"Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, and Haifeng Wang. 2022. UNIMO-2: End-to-End Unified Vision-Language Grounded Learning. arXiv preprint arXiv:2203.09067 (2022)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896494"},{"key":"e_1_3_2_2_30_1","volume-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. In ECCV. Springer, 121--137."},{"key":"e_1_3_2_2_31_1","volume-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208","author":"Li Yangguang","year":"2021","unstructured":"Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, and Junjie Yan. 2021. Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)."},{"key":"e_1_3_2_2_32_1","volume-title":"et al","author":"Lin Junyang","year":"2021","unstructured":"Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, et al . 2021. M6: A chinese multimodal pretrainer. arXiv preprint arXiv:2103.00823 (2021)."},{"key":"e_1_3_2_2_33_1","volume-title":"Microsoft coco: Common objects in context","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In ECCV. Springer, 740--755."},{"key":"e_1_3_2_2_34_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00397"},{"key":"e_1_3_2_2_36_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"e_1_3_2_2_42_1","volume-title":"Zihang Dai, Yulia Tsvetkov, and Yuan Cao.","author":"Wang Zirui","year":"2021","unstructured":"Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2021. Simvlm: Simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)."},{"key":"e_1_3_2_2_43_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_2_44_1","volume-title":"E2E-VLP: end-to-end vision-language pre-training enhanced by visual learning. arXiv preprint arXiv:2106.01804","author":"Xu Haiyang","year":"2021","unstructured":"Haiyang Xu, Ming Yan, Chenliang Li, Bin Bi, Songfang Huang, Wenming Xiao, and Fei Huang. 2021. E2E-VLP: end-to-end vision-language pre-training enhanced by visual learning. arXiv preprint arXiv:2106.01804 (2021)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0541-x"},{"key":"e_1_3_2_2_46_1","volume-title":"Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783","author":"Yao Lewei","year":"2021","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021. Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00414"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.160"}],"event":{"name":"WSDM '23: The Sixteenth ACM International Conference on Web Search and Data Mining","location":"Singapore Singapore","acronym":"WSDM '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570481","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:15Z","timestamp":1750186935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570481"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":50,"alternative-id":["10.1145\/3539597.3570481","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3570481","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}