{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T12:08:53Z","timestamp":1779192533029,"version":"3.51.4"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["23BGL306"],"award-info":[{"award-number":["23BGL306"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176011"],"award-info":[{"award-number":["62176011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["L241053"],"award-info":[{"award-number":["L241053"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.inffus.2026.104376","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T06:24:19Z","timestamp":1776234259000},"page":"104376","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Interest-aware dual alignments for multimedia recommendation"],"prefix":"10.1016","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-5128","authenticated-orcid":false,"given":"Meng","family":"Jian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5222-7159","authenticated-orcid":false,"given":"Zhuoyang","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feipeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7209-0215","authenticated-orcid":false,"given":"Lifang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.inffus.2026.104376_bib0001","first-page":"459","article-title":"News recommendation systems in the era of information overload","volume":"20","author":"Feng","year":"2021","journal-title":"J. Web Eng."},{"key":"10.1016\/j.inffus.2026.104376_bib0002","doi-asserted-by":"crossref","first-page":"5107","DOI":"10.1109\/TMM.2022.3187556","article-title":"Self-supervised learning for multimedia recommendation","volume":"25","author":"Tao","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104376_bib0003","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"VBPR: visual Bayesian personalized ranking from implicit feedback","volume":"30","author":"He","year":"2016"},{"key":"10.1016\/j.inffus.2026.104376_bib0004","series-title":"The Conference on ACM International Conference on Multimedia (ACM MM)","first-page":"3872","article-title":"Mining latent structures for multimedia recommendation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104376_bib0005","series-title":"Proceedings of the ACM Web Conference","first-page":"845","article-title":"Bootstrap latent representations for multi-modal recommendation","author":"Zhou","year":"2023"},{"key":"10.1016\/j.inffus.2026.104376_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103472","article-title":"Dual-layer cross-modal alignment recommendation based on the diffusion model","volume":"125","author":"Xiu","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104376_bib0007","series-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","article-title":"Continual multimodal contrastive learning","author":"Liu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104376_bib0008","series-title":"Proceedings of the ACM International Conference on Multimedia (ACM MM)","article-title":"Towards modality generalization: a benchmark and prospective analysis","author":"Liu","year":"2025"},{"issue":"9","key":"10.1016\/j.inffus.2026.104376_bib0009","doi-asserted-by":"crossref","first-page":"9154","DOI":"10.1109\/TKDE.2022.3221949","article-title":"Latent structure mining with contrastive modality fusion for multimedia recommendation","volume":"35","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"10.1016\/j.inffus.2026.104376_bib0010","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"8","key":"10.1016\/j.inffus.2026.104376_bib0011","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MC.2009.263","article-title":"Matrix factorization techniques for recommender systems","volume":"42","author":"Koren","year":"2009","journal-title":"Computer"},{"key":"10.1016\/j.inffus.2026.104376_bib0012","series-title":"Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"165","article-title":"Neural graph collaborative filtering","author":"Wang","year":"2019"},{"key":"10.1016\/j.inffus.2026.104376_bib0013","series-title":"Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"639","article-title":"LightGCN: simplifying and powering graph convolution network for recommendation","author":"He","year":"2020"},{"issue":"6","key":"10.1016\/j.inffus.2026.104376_bib0014","doi-asserted-by":"crossref","first-page":"3308","DOI":"10.1109\/TCSS.2022.3210567","article-title":"Learning distinct relationship in package recommendation with graph attention networks","volume":"10","author":"Lu","year":"2022","journal-title":"IEEE Trans. Comput. Social Syst."},{"issue":"1","key":"10.1016\/j.inffus.2026.104376_bib0015","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/TCSS.2022.3151822","article-title":"Joint multi-grained popularity-aware graph convolution collaborative filtering for recommendation","volume":"10","author":"Liu","year":"2022","journal-title":"IEEE Trans. Comput. Social Syst."},{"key":"10.1016\/j.inffus.2026.104376_bib0016","series-title":"Proceedings of the ACM International Conference on Web Search and Data Mining","first-page":"661","article-title":"DGRec: graph neural network for recommendation with diversified embedding generation","author":"Yang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104376_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103168","article-title":"PEARL: a dual-layer graph learning for multimodal recommendation","volume":"122","author":"Dang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104376_bib0018","series-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"585","article-title":"Towards universal sequence representation learning for recommender systems","author":"Hou","year":"2022"},{"key":"10.1016\/j.inffus.2026.104376_bib0019","series-title":"Proceedings of the ACM International Conference on Multimedia in Asia Workshops","article-title":"MMRec: simplifying multimodal recommendation","author":"Zhou","year":"2023"},{"key":"10.1016\/j.inffus.2026.104376_bib0020","series-title":"Proceedings of the European Conference on Artificial Intelligence","article-title":"Enhancing dyadic relations with homogeneous graphs for multimodal recommendation","author":"Zhou","year":"2023"},{"key":"10.1016\/j.inffus.2026.104376_bib0021","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"6576","article-title":"Multi-view graph convolutional network for multimedia recommendation","author":"Yu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104376_bib0022","series-title":"Proceedings of the Conference on ACM International Conference on Multimedia (ACM MM)","first-page":"7591","article-title":"DiffMM: multi-modal diffusion model for recommendation","author":"Jiang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104376_bib0023","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8454","article-title":"LGMRec: local and global graph learning for multimodal recommendation","volume":"38","author":"Guo","year":"2024"},{"key":"10.1016\/j.inffus.2026.104376_bib0024","series-title":"Proceedings of the ACM International Conference on Information and Knowledge Management","first-page":"3943","article-title":"Do we really need to drop items with missing modalities in multimodal recommendation?","author":"Malitesta","year":"2024"},{"key":"10.1016\/j.inffus.2026.104376_bib0025","series-title":"Proceedings of the ACM Web Conference","article-title":"Generating with fairness: a modality-diffused counterfactual framework for incomplete multimodal recommendations","author":"Li","year":"2025"},{"issue":"1","key":"10.1016\/j.inffus.2026.104376_bib0026","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1109\/TKDE.2023.3282907","article-title":"Self-supervised learning for recommender systems: a survey","volume":"36","author":"Yu","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.inffus.2026.104376_bib0027","series-title":"Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"726","article-title":"Self-supervised graph learning for recommendation","author":"Wu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104376_bib0028","series-title":"Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"1294","article-title":"Are graph augmentations necessary? simple graph contrastive learning for recommendation","author":"Yu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104376_bib0029","series-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"4252","article-title":"Adaptive graph contrastive learning for recommendation","author":"Jiang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104376_bib0030","doi-asserted-by":"crossref","unstructured":"Y. Zhang, Y. Zhang, Y. Zhang, L. Sang, Y. Yang, Unveiling contrastive learning\u2019s capability of neighborhood aggregation for collaborative filtering, arXiv: 2504.10113(2025).","DOI":"10.1145\/3726302.3730111"},{"key":"10.1016\/j.inffus.2026.104376_bib0031","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.inffus.2026.104376_bib0032","first-page":"28541","article-title":"LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Proc. Adv. Conf. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.inffus.2026.104376_bib0033","unstructured":"B. Hui, J. Yang, Z. Cui, J. Yang, D. Liu, L. Zhang, T. Liu, J. Zhang, B. Yu, K. Lu, et al., Qwen2.5-coder technical report, arXiv: 2409.12186(2024)."},{"key":"10.1016\/j.inffus.2026.104376_bib0034","first-page":"24261","article-title":"MLP-Mixer: an all-MLP architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Proc. Adv. Conf. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.inffus.2026.104376_bib0035","series-title":"Proceedings of Applications of Computing, Automation and Wireless Systems in Electrical Engineering","first-page":"873","article-title":"Comparative study of convolution neural network\u2019s Relu and Leaky-Relu activation functions","author":"Dubey","year":"2019"},{"issue":"7","key":"10.1016\/j.inffus.2026.104376_bib0036","doi-asserted-by":"crossref","first-page":"2494","DOI":"10.1109\/TMI.2020.2972701","article-title":"Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation","volume":"39","author":"Chen","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.inffus.2026.104376_bib0037","unstructured":"M. Tschannen, J. Djolonga, P.K. Rubenstein, S. Gelly, M. Lucic, On mutual information maximization for representation learning, arXiv: 1907.13625(2019)."},{"issue":"9","key":"10.1016\/j.inffus.2026.104376_bib0038","doi-asserted-by":"crossref","first-page":"5271","DOI":"10.1109\/TKDE.2025.3569097","article-title":"Hierarchical intent-based interest disentanglement for personalized recommendation","volume":"37","author":"Wang","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.inffus.2026.104376_bib0039","series-title":"Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"43","article-title":"Image-based recommendations on styles and substitutes","author":"McAuley","year":"2015"},{"issue":"1","key":"10.1016\/j.inffus.2026.104376_bib0040","first-page":"1","article-title":"SPrank: semantic path-based ranking for top-n recommendations using linked open data","volume":"8","author":"Noia","year":"2016","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"10.1016\/j.inffus.2026.104376_bib0041","unstructured":"D.P. Kingma, J. Ba, Adam: a method for stochastic optimization,arXiv: 1412.6980(2014)."},{"issue":"11","key":"10.1016\/j.inffus.2026.104376_bib0042","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002551?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002551?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:42:54Z","timestamp":1779190974000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526002551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":42,"alternative-id":["S1566253526002551"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104376","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Interest-aware dual alignments for multimedia recommendation","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104376","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104376"}}