{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:51Z","timestamp":1750219791553,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"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\/3539618.3591863","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"3405-3409","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8459-6849","authenticated-orcid":false,"given":"Zhigong","family":"Zhou","sequence":"first","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6777-8778","authenticated-orcid":false,"given":"Ning","family":"Ding","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5346-2925","authenticated-orcid":false,"given":"Xiaochuan","family":"Fan","sequence":"additional","affiliation":[{"name":"JD.com, California, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3445-7036","authenticated-orcid":false,"given":"Yue","family":"Shang","sequence":"additional","affiliation":[{"name":"JD.com, California, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5900-4773","authenticated-orcid":false,"given":"Yiming","family":"Qiu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8135-1061","authenticated-orcid":false,"given":"Jingwei","family":"Zhuo","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3808-7276","authenticated-orcid":false,"given":"Zhiwei","family":"Ge","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2100-3860","authenticated-orcid":false,"given":"Songlin","family":"Wang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0266-5059","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0345-334X","authenticated-orcid":false,"given":"Sulong","family":"Xu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8308-4822","authenticated-orcid":false,"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tel Aviv","author":"Chen Long","year":"2022","unstructured":"Long Chen, Yuhang Zheng, and Jun Xiao. 2022. Rethinking data augmentation for robust visual question answering. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXVI. Springer, 95--112."},{"key":"e_1_3_2_1_2_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17980--17989","author":"Hu Xiaowei","year":"2022","unstructured":"Xiaowei Hu, Zhe Gan, Jianfeng Wang, Zhengyuan Yang, Zicheng Liu, Yumao Lu, and Lijuan Wang. 2022. Scaling up vision-language pre-training for image captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17980--17989."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.012"},{"key":"e_1_3_2_1_8_1","volume-title":"Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes. arXiv preprint arXiv:2203.05082","author":"Jiang Yunjiang","year":"2022","unstructured":"Yunjiang Jiang, Han Zhang, Yiming Qiu, Yun Xiao, Bo Long, and Wen-Yun Yang. 2022. Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes. arXiv preprint arXiv:2203.05082 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467101"},{"key":"e_1_3_2_1_10_1","volume-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision-ECCV 2020: 16th European Conference","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 Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXX 16. Springer, 121--137."},{"key":"e_1_3_2_1_11_1","volume-title":"Interbert: Vision-and-language interaction for multi-modal pretraining. arXiv preprint arXiv:2003.13198","author":"Lin Junyang","year":"2020","unstructured":"Junyang Lin, An Yang, Yichang Zhang, Jie Liu, Jingren Zhou, and Hongxia Yang. 2020. Interbert: Vision-and-language interaction for multi-modal pretraining. arXiv preprint arXiv:2003.13198 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_13_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","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, Vol. 32 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search. arXiv preprint arXiv:2208.06150","author":"Qiu Yiming","year":"2022","unstructured":"Yiming Qiu, Chenyu Zhao, Han Zhang, Jingwei Zhuo, Tianhao Li, Xiaowei Zhang, Songlin Wang, Sulong Xu, Bo Long, and Wen-Yun Yang. 2022. Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search. arXiv preprint arXiv:2208.06150 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210152"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2926725"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835810"},{"key":"e_1_3_2_1_18_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3464927"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462988"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401446"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"}],"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\/3539618.3591863","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591863","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\/3539618.3591863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":24,"alternative-id":["10.1145\/3539618.3591863","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591863","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"}}]}}