{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:02:47Z","timestamp":1784131367764,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543873.3584627","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"356-360","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5090-9819","authenticated-orcid":false,"given":"Xiaoyang","family":"Zheng","sequence":"first","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9832-5764","authenticated-orcid":false,"given":"Zilong","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2124-953X","authenticated-orcid":false,"given":"Sen","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5855-3810","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7408-8514","authenticated-orcid":false,"given":"Tao","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1652-8526","authenticated-orcid":false,"given":"Qingwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3742-4910","authenticated-orcid":false,"given":"Xiaoyi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Wei-Cheng Chang Daniel Jiang Hsiang-Fu Yu Choon\u00a0Hui Teo Jiong Zhang Kai Zhong Kedarnath Kolluri Qie Hu Nikhil Shandilya Vyacheslav Ievgrafov 2021. Extreme multi-label learning for semantic matching in product search. In SIGKDD. 2643\u20132651.","DOI":"10.1145\/3447548.3467092"},{"key":"e_1_3_2_1_2_1","unstructured":"[2] Alibaba\u00a0Group Damo\u00a0Academy. 2021. http:\/\/proxima.alibaba-inc.com\/."},{"key":"e_1_3_2_1_3_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1).","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1)."},{"key":"e_1_3_2_1_4_1","volume-title":"Fashionbert: Text and image matching with adaptive loss for cross-modal retrieval. In SIGIR. 2251\u20132260.","author":"Gao Dehong","year":"2020","unstructured":"Dehong Gao, Linbo Jin, Ben Chen, Minghui Qiu, Peng Li, Yi Wei, Yi Hu, and Hao Wang. 2020. Fashionbert: Text and image matching with adaptive loss for cross-modal retrieval. In SIGIR. 2251\u20132260."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_6_1","volume-title":"On using very large target vocabulary for neural machine translation. arXiv preprint arXiv:1412.2007","author":"Jean S\u00e9bastien","year":"2014","unstructured":"S\u00e9bastien Jean, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio. 2014. On using very large target vocabulary for neural machine translation. arXiv preprint arXiv:1412.2007 (2014)."},{"key":"e_1_3_2_1_7_1","unstructured":"Junnan Li Ramprasaath\u00a0R Selvaraju Akhilesh\u00a0Deepak Gotmare Shafiq Joty Caiming Xiong and Steven Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. In NeurIPS."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Sen Li Fuyu Lv Taiwei Jin Guli Lin Keping Yang Xiaoyi Zeng Xiao-Ming Wu and Qianli Ma. 2021. Embedding-Based Product Retrieval in Taobao Search. In SIGKDD. 3181\u2013\u20133189.","DOI":"10.1145\/3447548.3467101"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Priyanka Nigam Yiwei Song Vijai Mohan Vihan Lakshman Weitian Ding Ankit Shingavi Choon\u00a0Hui Teo Hao Gu and Bing Yin. 2019. Semantic product search. In SIGKDD. 2876\u20132885.","DOI":"10.1145\/3292500.3330759"},{"key":"e_1_3_2_1_10_1","volume-title":"Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966","author":"Qi Di","year":"2020","unstructured":"Di Qi, Lin Su, Jia Song, Edward Cui, Taroon Bharti, and Arun Sacheti. 2020. Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Minghui Qiu Peng Li Chengyu Wang Haojie Pan Ang Wang Cen Chen Xianyan Jia Yaliang Li Jun Huang Deng Cai 2021. EasyTransfer: A Simple and Scalable Deep Transfer Learning Platform for NLP Applications. In CIKM. 4075\u20134084.","DOI":"10.1145\/3459637.3481911"},{"key":"e_1_3_2_1_12_1","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML Vol.\u00a0139. 8748\u20138763."},{"key":"e_1_3_2_1_13_1","volume-title":"The probabilistic relevance framework: BM25 and beyond","author":"Robertson Stephen","unstructured":"Stephen Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: BM25 and beyond. Now Publishers Inc."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"e_1_3_2_1_15_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS. 5998\u20136008."},{"key":"e_1_3_2_1_16_1","unstructured":"Wei Wang Bin Bi Ming Yan Chen Wu Jiangnan Xia Zuyi Bao Liwei Peng and Luo Si. 2020. StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding. In ICLR."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Rong Xiao Jianhui Ji Baoliang Cui Haihong Tang Wenwu Ou Yanghua Xiao Jiwei Tan and Xuan Ju. 2019. Weakly supervised co-training of query rewriting and semantic matching for e-commerce. In WSDM. 402\u2013410.","DOI":"10.1145\/3289600.3291039"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Shaowei Yao Jiwei Tan Xi Chen Keping Yang Rong Xiao Hongbo Deng and Xiaojun Wan. 2021. Learning a Product Relevance Model from Click-Through Data in E-Commerce. In WWW. 2890\u20132899.","DOI":"10.1145\/3442381.3450129"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539151"},{"key":"e_1_3_2_1_20_1","volume-title":"Vinvl: Revisiting visual representations in vision-language models. In CVPR. 5579\u20135588.","author":"Zhang Pengchuan","year":"2021","unstructured":"Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, Lijuan Wang, Yejin Choi, and Jianfeng Gao. 2021. Vinvl: Revisiting visual representations in vision-language models. In CVPR. 5579\u20135588."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Mingchen Zhuge Dehong Gao Deng-Ping Fan Linbo Jin Ben Chen Haoming Zhou Minghui Qiu and Ling Shao. 2021. Kaleido-BERT: Vision-Language Pre-training on Fashion Domain. In CVPR. 12647\u201312657.","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"e_1_3_2_1_22_1","volume-title":"Inverted files for text search engines. ACM computing surveys (CSUR) 38, 2","author":"Zobel Justin","year":"2006","unstructured":"Justin Zobel and Alistair Moffat. 2006. Inverted files for text search engines. ACM computing surveys (CSUR) 38, 2 (2006), 6\u2013es."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3584627","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3584627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:33:14Z","timestamp":1755819194000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3584627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":22,"alternative-id":["10.1145\/3543873.3584627","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3584627","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}