{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:49:36Z","timestamp":1761396576067,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"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":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591859","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"3385-3389","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Delving into E-Commerce Product Retrieval with Vision-Language Pre-training"],"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, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5918-093X","authenticated-orcid":false,"given":"Fuyu","family":"Lv","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9832-5764","authenticated-orcid":false,"given":"Zilong","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1652-8526","authenticated-orcid":false,"given":"Qingwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3742-4910","authenticated-orcid":false,"given":"Xiaoyi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Hinton","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In ICML (Proceedings of Machine Learning Research, Vol. 119). PMLR, 1597--1607."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23052-9"},{"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--2260.","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--2260."},{"key":"e_1_3_2_1_5_1","volume-title":"Girshick","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In CVPR. Computer Vision Foundation \/ IEEE, 9726--9735."},{"key":"e_1_3_2_1_6_1","volume-title":"USENIX Annual Technical Conference. USENIX Association, 673--688","author":"Jia Xianyan","year":"2022","unstructured":"Xianyan Jia, Le Jiang, Ang Wang, Wencong Xiao, Ziji Shi, Jie Zhang, Xinyuan Li, Langshi Chen, Yong Li, Zhen Zheng, Xiaoyong Liu, and Wei Lin. 2022. Whale: Efficient Giant Model Training over Heterogeneous GPUs. In USENIX Annual Technical Conference. USENIX Association, 673--688."},{"key":"e_1_3_2_1_7_1","volume-title":"Fixing Weight Decay Regularization in Adam. CoRR","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Fixing Weight Decay Regularization in Adam. CoRR, Vol. abs\/1711.05101 (2017)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_1_9_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 et al. 2021. EasyTransfer: A Simple and Scalable Deep Transfer Learning Platform for NLP Applications. In CIKM. 4075--4084.","DOI":"10.1145\/3459637.3481911"},{"key":"e_1_3_2_1_10_1","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume":"139","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML, Vol. 139. 8748--8763.","journal-title":"ICML"},{"key":"e_1_3_2_1_11_1","volume-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents. CoRR","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. CoRR, Vol. abs\/2204.06125 (2022)."},{"key":"e_1_3_2_1_12_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS. 5998--6008."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Jinpeng Wang Jieming Zhu and Xiuqiang He. 2021. Cross-Batch Negative Sampling for Training Two-Tower Recommenders. In SIGIR. ACM 1632--1636.","DOI":"10.1145\/3404835.3463032"},{"key":"e_1_3_2_1_14_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_15_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--2899.","DOI":"10.1145\/3442381.3450129"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539151"},{"key":"e_1_3_2_1_17_1","volume-title":"MAKE: Product Retrieval with Vision-Language Pre-training in Taobao Search. CoRR","author":"Zheng Xiaoyang","year":"2023","unstructured":"Xiaoyang Zheng, Zilong Wang, Sen Li, Ke Xu, Tao Zhuang, Qingwen Liu, and Xiaoyi Zeng. 2023. MAKE: Product Retrieval with Vision-Language Pre-training in Taobao Search. CoRR, Vol. abs\/2301.12646 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Lixin Zou Shengqiang Zhang Hengyi Cai Dehong Ma Suqi Cheng Shuaiqiang Wang Daiting Shi Zhicong Cheng and Dawei Yin. 2021. Pre-trained Language Model based Ranking in Baidu Search. In KDD. ACM 4014--4022.","DOI":"10.1145\/3447548.3467147"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Taipei Taiwan","acronym":"SIGIR '23"},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591859","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:59Z","timestamp":1750178279000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591859"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":18,"alternative-id":["10.1145\/3539618.3591859","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591859","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}