{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:10:11Z","timestamp":1780765811931,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":41,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3539597.3570423","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"1039-1047","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Multimodal Pre-Training with Self-Distillation for Product Understanding in E-Commerce"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2976-6256","authenticated-orcid":false,"given":"Shilei","family":"Liu","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6606-8831","authenticated-orcid":false,"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5778-6452","authenticated-orcid":false,"given":"Jun","family":"Song","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3853-066X","authenticated-orcid":false,"given":"Yonghua","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, 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, Hangzhou, 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":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031-00129--1_21"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_2_6_1","volume-title":"Proc. of AACL.","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 Proc. of AACL."},{"key":"e_1_3_2_2_7_1","unstructured":"Xiao Dong Xunlin Zhan Yangxin Wu Yunchao Wei Xiaoyong Wei Minlong Lu and Xiaodan Liang. 2021. M5Product: A Multi-modal Pretraining Benchmark for E-commercial Product Downstream Tasks. (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"Proc. of ICLR.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proc. of ICLR."},{"key":"e_1_3_2_2_9_1","unstructured":"Chenzhuang Du Tingle Li Yichen Liu Zixin Wen Tianyu Hua Yue Wang and Hang Zhao. 2021. Improving Multi-Modal Learning with Uni-Modal Teachers. In arXiv: 2106.11059."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"e_1_3_2_2_11_1","volume-title":"Girshick","author":"He Kaiming","year":"2021","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross B. Girshick. 2021. Masked Autoencoders Are Scalable Vision Learners. In arXiv: 2111.06377."},{"key":"e_1_3_2_2_12_1","volume-title":"Piotr Doll\u00e1 r, and Ross B. Girshick","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1 r, and Ross B. Girshick. 2017. Mask R-CNN. In Proc. of ICCV."},{"key":"e_1_3_2_2_13_1","unstructured":"Geoffrey E. Hinton Oriol Vinyals and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv: 2203.05557."},{"key":"e_1_3_2_2_14_1","volume-title":"ICML'21","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 ICML'21."},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. of ICLR'20","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In Proc. of ICLR'20."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467206"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_19_1","volume-title":"Proc. of NeurIPS.","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. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_20_1","volume-title":"Proc. of NeurIPS.","author":"Nagrani Arsha","year":"2021","unstructured":"Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, and Chen Sun. 2021. Attention Bottlenecks for Multimodal Fusion. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_2_22_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In ICML'21","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'21."},{"key":"e_1_3_2_2_23_1","volume-title":"FLAVA: A Foundational Language And Vision Alignment Model. In arXiv: 2112.04482.","author":"Singh Amanpreet","year":"2021","unstructured":"Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon, Wojciech Galuba, Marcus Rohrbach, and Douwe Kiela. 2021. FLAVA: A Foundational Language And Vision Alignment Model. In arXiv: 2112.04482."},{"key":"e_1_3_2_2_24_1","volume-title":"Proc. of ICLR.","author":"Su Weijie","year":"2020","unstructured":"Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In Proc. of ICLR."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3101421"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_27_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_2_29_1","volume-title":"ICML'22","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework. In ICML'22."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3291039"},{"key":"e_1_3_2_2_32_1","volume-title":"Piotr Doll\u00e1 r, and Ross B. Girshick","author":"Xiao Tete","year":"2021","unstructured":"Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Doll\u00e1 r, and Ross B. Girshick. 2021. Early Convolutions Help Transformers See Better. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_33_1","unstructured":"Zhenda Xie Zheng Zhang Yue Cao Yutong Lin Jianmin Bao Zhuliang Yao Qi Dai and Han Hu. 2021. SimMIM: A Simple Framework for Masked Image Modeling. arXiv: 2111.09886."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Jinyu Yang Jiali Duan Son Tran Yi Xu Sampath Chanda Liqun Chen Belinda Zeng Trishul Chilimbi and Junzhou Huang. 2022a. Vision-Language Pre-Training with Triple Contrastive Learning. arXiv: 2202.10401.","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498377"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450129"},{"key":"e_1_3_2_2_37_1","volume-title":"ICLR'20","author":"You Yang","year":"2020","unstructured":"Yang You, Jing Li, Sashank J. Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, and Cho-Jui Hsieh. 2020. Large Batch Optimization for Deep Learning: Training BERT in 76 minutes. In ICLR'20."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01157"},{"key":"e_1_3_2_2_39_1","volume-title":"Chi","author":"Zhao Qian","year":"2018","unstructured":"Qian Zhao, Jilin Chen, Minmin Chen, Sagar Jain, Alex Beutel, Francois Belletti, and Ed H. Chi. 2018. Categorical-attributes-based item classification for recommender systems. In RecSys'19."},{"key":"e_1_3_2_2_40_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Conditional Prompt Learning for Vision-Language Models. arXiv: 2203.05557."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"}],"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\/3539597.3570423","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:14Z","timestamp":1750186934000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570423"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":41,"alternative-id":["10.1145\/3539597.3570423","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3570423","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"}}]}}