{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:47Z","timestamp":1781538887902,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172156"],"award-info":[{"award-number":["62172156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Hunan Province","award":["2026JJ50527"],"award-info":[{"award-number":["2026JJ50527"]}]},{"name":"Yuelushan Digital Intelligence Laboratory(Artificial Intelligence & International Communication, HNNU)","award":["KF700201025004"],"award-info":[{"award-number":["KF700201025004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810591","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"298-307","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CREAM: Collaborative Representation with Self-supervised Alignment for Multimedia Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5567-1325","authenticated-orcid":false,"given":"Junhao","family":"Gao","sequence":"first","affiliation":[{"name":"Hunan University, College of Computer Science and Electronic Engineering, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8774-8115","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan University, College of Computer Science and Electronic Engineering, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5840-9664","authenticated-orcid":false,"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hunan University, College of Computer Science and Electronic Engineering, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Jie Chen Haw-ren Fang et\u00a0al. 2009. Fast Approximate kNN Graph Construction for High Dimensional Data via Recursive Lanczos Bisection.Journal of Machine Learning Research 10 9 (2009)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Jiayu Cui Yuanye Liu Renwei Dian Shutao Li and Jinyang Liu. 2026. Dual-Stream Hierarchical Mamba for High-Resolution Hyperspectral Fusion Imaging. Information Fusion (2026) 104244.","DOI":"10.1016\/j.inffus.2026.104244"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Yashar Deldjoo Fatemeh Nazary Arnau Ramisa Julian Mcauley Giovanni Pellegrini Alejandro Bellogin and Tommaso\u00a0Di Noia. 2023. A review of modern fashion recommender systems. Comput. Surveys 56 4 (2023) 1\u201337.","DOI":"10.1145\/3624733"},{"key":"e_1_3_3_2_7_2","first-page":"249","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_3_2_12_2","unstructured":"Zhuangzhuang He Zihan Wang Yonghui Yang Haoyue Bai and Le Wu. 2024. Boosting Multimedia Recommendation via Separate Generic and Unique Awareness. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.08270 (2024)."},{"key":"e_1_3_3_2_13_2","unstructured":"Zhuangzhuang He Zihan Wang Yonghui Yang Haoyue Bai and Le Wu. 2024. It is Never Too Late to Mend: Separate Learning for Multimedia Recommendation."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33283"},{"key":"e_1_3_3_2_15_2","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1412.6980 (2014)."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Yehuda Koren Steffen Rendle and Robert Bell. 2021. Advances in collaborative filtering. Recommender systems handbook (2021) 91\u2013142.","DOI":"10.1007\/978-1-0716-2197-4_3"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Qidong Liu Jiaxi Hu Yutian Xiao Xiangyu Zhao Jingtong Gao Wanyu Wang Qing Li and Jiliang Tang. 2024. Multimodal recommender systems: A survey. Comput. Surveys 57 2 (2024) 1\u201317.","DOI":"10.1145\/3695461"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080658"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313513"},{"key":"e_1_3_3_2_20_2","unstructured":"Weiming Liu Chaochao Chen Jiahe Xu Xinting Liao Fan Wang Xiaolin Zheng Zhihui Fu Ruiguang Pei and Jun Wang. 2025. Joint Similarity Item Exploration and Overlapped User Guidance for Multi-Modal Cross-Domain Recommendation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.16068 (2025)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Xiao Liu Fanjin Zhang Zhenyu Hou Li Mian Zhaoyu Wang Jing Zhang and Jie Tang. 2021. Self-supervised learning: Generative or contrastive. IEEE transactions on knowledge and data engineering 35 1 (2021) 857\u2013876.","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679626"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731715.3733382"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482291"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_3_2_26_2","first-page":"2554","volume-title":"International conference on machine learning","author":"Munkhdalai Tsendsuren","year":"2017","unstructured":"Tsendsuren Munkhdalai and Hong Yu. 2017. Meta networks. In International conference on machine learning. PMLR, 2554\u20132563."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Jose\u00a0C Principe Dongxin Xu Qun Zhao and John\u00a0W Fisher. 2000. Learning from examples with information theoretic criteria. Journal of VLSI signal processing systems for signal image and video technology 26 (2000) 61\u201377.","DOI":"10.1023\/A:1008143417156"},{"key":"e_1_3_3_2_28_2","unstructured":"Steffen Rendle Christoph Freudenthaler Zeno Gantner and Lars Schmidt-Thieme. 2012. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1205.2618 (2012)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Brent Smith and Greg Linden. 2017. Two decades of recommender systems at Amazon. com. Ieee internet computing 21 3 (2017) 12\u201318.","DOI":"10.1109\/MIC.2017.72"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Jinhui Tang Xiaoyu Du Xiangnan He Fajie Yuan Qi Tian and Tat-Seng Chua. 2019. Adversarial training towards robust multimedia recommender system. IEEE Transactions on Knowledge and Data Engineering 32 5 (2019) 855\u2013867.","DOI":"10.1109\/TKDE.2019.2893638"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Zhulin Tao Xiaohao Liu Yewei Xia Xiang Wang Lifang Yang Xianglin Huang and Tat-Seng Chua. 2022. Self-supervised learning for multimedia recommendation. IEEE Transactions on Multimedia 25 (2022) 5107\u20135116.","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_3_2_33_2","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9 11 (2008)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583206"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532058"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Teng Xiao Huaisheng Zhu Zhengyu Chen and Suhang Wang. 2023. Simple and asymmetric graph contrastive learning without augmentations. Advances in neural information processing systems 36 (2023) 16129\u201316152.","DOI":"10.52202\/075280-0710"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33408"},{"key":"e_1_3_3_2_41_2","unstructured":"Jinfeng Xu Zheyu Chen Shuo Yang Jinze Li Wei Wang Xiping Hu Steven Hoi and Edith Ngai. 2025. A Survey on Multimodal Recommender Systems: Recent Advances and Future Directions. arxiv:https:\/\/arXiv.org\/abs\/2502.15711\u00a0[cs.IR] https:\/\/arxiv.org\/abs\/2502.15711"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688096"},{"key":"e_1_3_3_2_43_2","unstructured":"Wenzhe Yin Zehao Xiao Pan Zhou Shujian Yu Jiayi Shen Jan-Jakob Sonke and Efstratios Gavves. 2025. Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.17028 (2025)."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33429"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_3_2_48_2","unstructured":"Xiangyu Zhao Yichao Wang Bo Chen Jingtong Gao Yuhao Wang Xiaopeng Li Pengyue Jia Qidong Liu Huifeng Guo and Ruiming Tang. 2025. Joint Modeling in Recommendations: A Survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.21195 (2025)."},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608811"},{"key":"e_1_3_3_2_50_2","unstructured":"Hongyu Zhou Xin Zhou Zhiwei Zeng Lingzi Zhang and Zhiqi Shen. 2023. A comprehensive survey on multimodal recommender systems: Taxonomy evaluation and future directions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.04473 (2023)."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611380.3628561"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00100"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:03:22Z","timestamp":1781535802000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":53,"alternative-id":["10.1145\/3805622.3810591","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810591","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}