{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:41Z","timestamp":1786120841134,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["92570204, 62441235, 62502264"],"award-info":[{"award-number":["92570204, 62441235, 62502264"]}]},{"name":"Beijing Natural Science Foundation","award":["L257005"],"award-info":[{"award-number":["L257005"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818176","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"1486-1497","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-Guided Visual Representation Learning for Robust Multimodal E-Commerce Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2594-3179","authenticated-orcid":false,"given":"Yufei","family":"Guo","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4443-0215","authenticated-orcid":false,"given":"Jing","family":"Ma","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4962-6253","authenticated-orcid":false,"given":"Yixuan","family":"Dong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4592-5448","authenticated-orcid":false,"given":"Tianlu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8756-8636","authenticated-orcid":false,"given":"Shijie","family":"Yang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7891-0221","authenticated-orcid":false,"given":"Yanlong","family":"Zang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0798-0243","authenticated-orcid":false,"given":"Weijie","family":"Ding","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6889-6792","authenticated-orcid":false,"given":"Pinghua","family":"Gong","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736.","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_1_2_1","unstructured":"Shuai Bai Yuxuan Cai Ruizhe Chen Keqin Chen Xionghui Chen Zesen Cheng Lianghao Deng Wei Ding Chang Gao Chunjiang Ge Wenbin Ge Zhifang Guo Qidong Huang Jie Huang Fei Huang Binyuan Hui Shutong Jiang Zhaohai Li Mingsheng Li Mei Li Kaixin Li Zicheng Lin Junyang Lin Xuejing Liu Jiawei Liu Chenglong Liu Yang Liu Dayiheng Liu Shixuan Liu Dunjie Lu Ruilin Luo Chenxu Lv Rui Men Lingchen Meng Xuancheng Ren Xingzhang Ren Sibo Song Yuchong Sun Jun Tang Jianhong Tu Jianqiang Wan Peng Wang Pengfei Wang Qiuyue Wang Yuxuan Wang Tianbao Xie Yiheng Xu Haiyang Xu Jin Xu Zhibo Yang Mingkun Yang Jianxin Yang An Yang Bowen Yu Fei Zhang Hang Zhang Xi Zhang Bo Zheng Humen Zhong Jingren Zhou Fan Zhou Jing Zhou Yuanzhi Zhu and Ke Zhu. 2025a. Qwen3-VL Technical Report. ArXiv Vol. abs\/2511.21631 (2025)."},{"key":"e_1_3_2_1_3_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025b. Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_7_1","first-page":"49250","volume-title":"Levine (Eds.)","volume":"36","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, DongXu Li, Anthony Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 49250-49267. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/9a6a435e75419a836fe47ab6793623e6-Paper-Conference.pdf"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00304"},{"key":"e_1_3_2_1_9_1","unstructured":"Xiuqi Deng Lu Xu Xiyao Li Jinkai Yu Erpeng Xue Zhongyuan Wang Di Zhang Zhaojie Liu Guorui Zhou Yang Song et al. 2024. End-to-End Training of Multimodal Model and Ranking Model. arXiv preprint arXiv:2404.06078 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"e_1_3_2_1_11_1","first-page":"2669","volume-title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Han Xiao","year":"2023","unstructured":"Xiao Han, Xiatian Zhu, Licheng Yu, Li Zhang, Yi-Zhe Song, and Tao Xiang. 2023. FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023), 2669-2680."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_24"},{"key":"e_1_3_2_1_13_1","volume-title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs. In International Conference on Learning Representations (ICLR)","volume":"2107","author":"Jaegle Andrew","year":"2022","unstructured":"Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Andrew Zisserman, Oriol Vinyals, and Joao Carreira. 2022. Perceiver IO: A General Architecture for Structured Inputs & Outputs. In International Conference on Learning Representations (ICLR), Vol. abs\/2107.14795."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research","volume":"4664","author":"Jaegle Andrew","year":"2021","unstructured":"Andrew Jaegle, Felix Gimeno, Andrew Brock, Andrew Zisserman, Oriol Vinyals, and Joao Carreira. 2021. Perceiver: General Perception with Iterative Attention. In Proceedings of the 38th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 4651-4664. http:\/\/proceedings.mlr.press"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 4904-4916. http:\/\/proceedings.mlr.press\/v139\/jia21b.html"},{"key":"e_1_3_2_1_16_1","first-page":"11060","volume-title":"Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Jin Yang","year":"2023","unstructured":"Yang Jin, Yongzhi Li, Zehuan Yuan, and Yadong Mu. 2023. Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023), 11060-11069."},{"key":"e_1_3_2_1_17_1","volume-title":"Billion-scale similarity search with GPUs. CoRR","author":"Johnson Jeff","year":"2017","unstructured":"Jeff Johnson, Matthijs Douze, and Herv\u00e9 J\u00e9gou. 2017. Billion-scale similarity search with GPUs. CoRR, Vol. abs\/1702.08734 (2017). http:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1702.html#JohnsonDJ17"},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 12888-12900."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761170"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_23_1","first-page":"34892","volume-title":"Levine (Eds.)","volume":"36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 34892-34916. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3478848"},{"key":"e_1_3_2_1_26_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01291-2"},{"key":"e_1_3_2_1_29_1","volume-title":"Ngai","author":"Xu Jinfeng","year":"2025","unstructured":"Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Wei Wang, Xiping Hu, Steven Hoi, and Edith C. H. Ngai. 2025. A Survey on Multimodal Recommender Systems: Recent Advances and Future Directions. ArXiv, Vol. abs\/2502.15711 (2025)."},{"key":"e_1_3_2_1_30_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_31_1","volume-title":"Chinese clip: Contrastive vision-language pretraining in chinese. arXiv preprint arXiv:2211.01335","author":"Yang An","year":"2022","unstructured":"An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, and Chang Zhou. 2022. Chinese clip: Contrastive vision-language pretraining in chinese. arXiv preprint arXiv:2211.01335 (2022)."},{"key":"e_1_3_2_1_32_1","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Ce Bian Chao Yin Chenxu Lv Da Pan Dian Wang Dong Yan et al. 2023. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Large scale product graph construction for recommendation in e-commerce. arXiv preprint arXiv:2010.05525","author":"Yang Xiaoyong","year":"2020","unstructured":"Xiaoyong Yang, Yadong Zhu, Yi Zhang, Xiaobo Wang, and Quan Yuan. 2020. Large scale product graph construction for recommendation in e-commerce. arXiv preprint arXiv:2010.05525 (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"Florence: A New Foundation Model for Computer Vision. ArXiv","author":"Yuan Lu","year":"2021","unstructured":"Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, Jianfeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, and Pengchuan Zhang. 2021. Florence: A New Foundation Model for Computer Vision. ArXiv, Vol. abs\/2111.11432 (2021)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709440"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_1_37_1","volume-title":"Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176","author":"Zhang Yanzhao","year":"2025","unstructured":"Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al., 2025a. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025)."},{"key":"e_1_3_2_1_38_1","unstructured":"Jinguo Zhu Weiyun Wang Zhe Chen Zhaoyang Liu Shenglong Ye Lixin Gu Hao Tian Yuchen Duan Weijie Su Jie Shao et al. 2025. Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:19:24Z","timestamp":1786065564000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":38,"alternative-id":["10.1145\/3770855.3818176","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818176","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}