{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T17:15:26Z","timestamp":1785863726063,"version":"3.56.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072288"],"award-info":[{"award-number":["62072288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10489-024-06061-1","type":"journal-article","created":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T08:19:50Z","timestamp":1731917990000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Towards user-specific multimodal recommendation via cross-modal attention-enhanced graph convolution network"],"prefix":"10.1007","volume":"55","author":[{"given":"Ruidong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5880-0225","authenticated-orcid":false,"given":"Zhongying","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,18]]},"reference":[{"key":"6061_CR1","doi-asserted-by":"publisher","unstructured":"Gu S, Wang X, Shi C, Xiao D (2022) Self-supervised graph neural networks for multi-behavior recommendation. In: Proceedings of the thirty-first international joint conference on artificial intelligence, pp 2052\u20132058. https:\/\/doi.org\/10.24963\/ijcai.2022\/285","DOI":"10.24963\/ijcai.2022\/285"},{"key":"6061_CR2","doi-asserted-by":"publisher","unstructured":"Chen J, Zhang H, He X, Nie L, Liu W, Chua T-S (2017) Attentive collaborative filtering: multimedia recommendation with item- and component-level attention. In: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval. https:\/\/doi.org\/10.1145\/3077136.3080797","DOI":"10.1145\/3077136.3080797"},{"key":"6061_CR3","doi-asserted-by":"publisher","unstructured":"Chen L, Wu L, Hong R, Zhang K, Wang M (2020) Revisiting graph based collaborative filtering: a linear residual graph convolutional network approach. In: Proceedings of the AAAI conference on artificial intelligence, pp 27\u201334. https:\/\/doi.org\/10.1609\/aaai.v34i01.5330","DOI":"10.1609\/aaai.v34i01.5330"},{"key":"6061_CR4","doi-asserted-by":"publisher","unstructured":"He X, Deng K, Wang X, Li Y, Zhang Y, Wang M (2020) Lightgcn: simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, pp 639\u2013648. https:\/\/doi.org\/10.1145\/3397271.3401063","DOI":"10.1145\/3397271.3401063"},{"key":"6061_CR5","doi-asserted-by":"publisher","unstructured":"Yue G, Xiao R, Zhao Z, Li C (2023) AF-GCN: attribute-fusing graph convolution network for recommendation. IEEE Trans Big Data:597\u2013607. https:\/\/doi.org\/10.1109\/TBDATA.2022.3192598","DOI":"10.1109\/TBDATA.2022.3192598"},{"key":"6061_CR6","doi-asserted-by":"publisher","unstructured":"Li S, Guo D, Liu K, Hong R, Xue F (2023) Multimodal counterfactual learning network for multimedia-based recommendation. In: Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval, pp 1539\u20131548. https:\/\/doi.org\/10.1145\/3539618.3591739","DOI":"10.1145\/3539618.3591739"},{"key":"6061_CR7","doi-asserted-by":"publisher","unstructured":"Liu K, Xue F, Guo D, Wu L, Li S, Hong R (2023) MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation. ACM Trans Inform Syst:1\u201327. https:\/\/doi.org\/10.1145\/3544106","DOI":"10.1145\/3544106"},{"key":"6061_CR8","doi-asserted-by":"publisher","unstructured":"Mu Z, Zhuang Y, Tan J, Xiao J, Tang S (2022) Learning hybrid behavior patterns for multimedia recommendation. In: Proceedings of the 30th ACM international conference on multimedia, pp 376\u2013384. https:\/\/doi.org\/10.1145\/3503161.3548119","DOI":"10.1145\/3503161.3548119"},{"key":"6061_CR9","doi-asserted-by":"publisher","unstructured":"He R, McAuley J (2016) VBPR: visual Bayesian personalized ranking from implicit feedback. In: Proceedings of the Thirtieth AAAI conference on artificial intelligence, pp 144\u2013150. https:\/\/doi.org\/10.5555\/3015812.3015834","DOI":"10.5555\/3015812.3015834"},{"key":"6061_CR10","doi-asserted-by":"publisher","unstructured":"Rendle S, Freudenthaler C, Gantner Z, Schmidt-Thieme L (2009) BPR: Bayesian personalized ranking from implicit feedback. In: Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence, pp 452\u2013461. https:\/\/doi.org\/10.5555\/1795114.1795167","DOI":"10.5555\/1795114.1795167"},{"key":"6061_CR11","doi-asserted-by":"publisher","unstructured":"Wei Y, Wang X, Nie L, He X, Hong R, Chua T-S (2019) MMGCN: multi-modal graph convolution network for personalized recommendation of micro-video. In: Proceedings of the 27th ACM international conference on multimedia, pp 1437\u20131445. https:\/\/doi.org\/10.1145\/3343031.3351034","DOI":"10.1145\/3343031.3351034"},{"key":"6061_CR12","doi-asserted-by":"publisher","unstructured":"Zhang J, Zhu Y, Liu Q, Wu S, Wang S, Wang L (2021) Mining Latent Structures for Multimedia Recommendation. In: Proceedings of the 29th ACM international conference on multimedia. https:\/\/doi.org\/10.1145\/3474085.3475259","DOI":"10.1145\/3474085.3475259"},{"key":"6061_CR13","doi-asserted-by":"publisher","unstructured":"Kim T, Lee Y-C, Shin K, Kim S-W (2022) MARIO: modality-aware attention and modality-preserving decoders for multimedia recommendation. In: Proceedings of the 31st ACM international conference on information & knowledge management, pp 993\u20131002. https:\/\/doi.org\/10.1145\/3511808.3557387","DOI":"10.1145\/3511808.3557387"},{"key":"6061_CR14","doi-asserted-by":"publisher","unstructured":"Zhang J, Zhu Y, Liu Q, Zhang M, Wu S, Wang L (2023) Latent Structure Mining With Contrastive Modality Fusion for Multimedia Recommendation. IEEE Trans Knowl Data Eng:9154\u20139167. https:\/\/doi.org\/10.1109\/TKDE.2022.3221949","DOI":"10.1109\/TKDE.2022.3221949"},{"key":"6061_CR15","doi-asserted-by":"publisher","unstructured":"Zhou X, Zhou H, Liu Y, Zeng Z, Miao C, Wang P, You Y, Jiang F (2023) Bootstrap Latent Representations for Multi-modal Recommendation. In: Proceedings of the ACM web conference 2023. https:\/\/doi.org\/10.1145\/3543507.3583251","DOI":"10.1145\/3543507.3583251"},{"key":"6061_CR16","doi-asserted-by":"publisher","unstructured":"Wei W, Huang C, Xia L, Zhang C (2023) Multi-modal self-supervised learning for recommendation. In: Proceedings of the ACM web conference 2023. https:\/\/doi.org\/10.1145\/3543507.3583206","DOI":"10.1145\/3543507.3583206"},{"key":"6061_CR17","doi-asserted-by":"publisher","unstructured":"Zhang Q, Zhao Z, Zhou H, Li X, Li C (2023) Self-supervised contrastive learning on heterogeneous graphs with mutual constraints of structure and feature. Inform Sci:119026. https:\/\/doi.org\/10.1016\/j.ins.2023.119026","DOI":"10.1016\/j.ins.2023.119026"},{"key":"6061_CR18","doi-asserted-by":"publisher","unstructured":"Zhao Z, Yang Z, Li C, Zeng Q, Guan W, Zhou M (2023) Dual Feature Interaction-Based Graph Convolutional Network. IEEE Trans Knowl Data Eng:9019\u20139030. https:\/\/doi.org\/10.1109\/TKDE.2022.3220789","DOI":"10.1109\/TKDE.2022.3220789"},{"key":"6061_CR19","doi-asserted-by":"publisher","unstructured":"Yang L, Wang S, Tao Y, Sun J, Liu X, Yu PS, Wang T (2023) DGRec: graph neural network for recommendation with diversified embedding generation. In: Proceedings of the sixteenth ACM international conference on web search and data mining, pp 661\u2013669. https:\/\/doi.org\/10.1145\/3539597.3570472","DOI":"10.1145\/3539597.3570472"},{"key":"6061_CR20","doi-asserted-by":"publisher","unstructured":"Cai L, Li J, Wang J, Ji S (2022) Line graph neural networks for link prediction. IEEE Trans Pattern Anal Mach Intell:5103\u20135113. https:\/\/doi.org\/10.1109\/TPAMI.2021.3080635","DOI":"10.1109\/TPAMI.2021.3080635"},{"key":"6061_CR21","doi-asserted-by":"publisher","unstructured":"Wang X, He X, Wang M, Feng F, Chua T-S (2019) Neural graph collaborative filtering. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval. https:\/\/doi.org\/10.1145\/3331184.3331267","DOI":"10.1145\/3331184.3331267"},{"key":"6061_CR22","doi-asserted-by":"publisher","unstructured":"Liu F, Cheng Z, Zhu L, Gao Z, Nie L (2021) Interest-aware message-passing GCN for recommendation. In: Proceedings of the web conference 2021, pp 1296\u20131305. https:\/\/doi.org\/10.1145\/3442381.3449986","DOI":"10.1145\/3442381.3449986"},{"key":"6061_CR23","doi-asserted-by":"publisher","unstructured":"Cai D, Qian S, Fang Q, Xu C (2022) Heterogeneous hierarchical feature aggregation network for personalized micro-video recommendation. IEEE Trans Multimedia:805\u2013818. https:\/\/doi.org\/10.1109\/TMM.2021.3059508","DOI":"10.1109\/TMM.2021.3059508"},{"key":"6061_CR24","doi-asserted-by":"publisher","unstructured":"Liu S, Chen Z, Liu H, Hu X (2019) User-video co-attention network for personalized micro-video recommendation. In: The world wide web conference, pp 3020\u20133026. https:\/\/doi.org\/10.1145\/3308558.3313513","DOI":"10.1145\/3308558.3313513"},{"key":"6061_CR25","doi-asserted-by":"publisher","unstructured":"Yang L, Liu Z, Wang Y, Wang C, Fan Z, Yu PS (2022) Large-scale personalized video game recommendation via social-aware contextualized graph neural network. In: Proceedings of the ACM web conference 2022, pp 3376\u20133386. https:\/\/doi.org\/10.1145\/3485447.3512273","DOI":"10.1145\/3485447.3512273"},{"key":"6061_CR26","doi-asserted-by":"publisher","unstructured":"Yu J, Yin H, Li J, Wang Q, Hung NQV, Zhang X (2021) Self-supervised multi-channel hypergraph convolutional network for social recommendation. In: Proceedings of the web conference 2021, pp 413\u2013424. https:\/\/doi.org\/10.1145\/3442381.3449844","DOI":"10.1145\/3442381.3449844"},{"key":"6061_CR27","doi-asserted-by":"publisher","unstructured":"Wang Z, Wei W, Cong G, Li X-L, Mao X-L, Qiu M (2020) Global context enhanced graph neural networks for session-based recommendation. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, pp 169\u2013178. https:\/\/doi.org\/10.1145\/3397271.3401142","DOI":"10.1145\/3397271.3401142"},{"key":"6061_CR28","doi-asserted-by":"publisher","unstructured":"Velickovic P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y (2018) Graph attention networks. In: 6th International conference on learning representations. https:\/\/doi.org\/10.1007\/978-3-031-01587-8_7","DOI":"10.1007\/978-3-031-01587-8_7"},{"key":"6061_CR29","doi-asserted-by":"publisher","unstructured":"Tao Z, Wei Y, Wang X, He X, Huang X, Chua T-S (2020) MGAT: multimodal graph attention network for recommendation. Inform Process Manag:102277. https:\/\/doi.org\/10.1016\/j.ipm.2020.102277","DOI":"10.1016\/j.ipm.2020.102277"},{"key":"6061_CR30","doi-asserted-by":"publisher","unstructured":"Wang X, He X, Cao Y, Liu M, Chua T-S (2019) KGAT: Knowledge graph attention network for recommendation. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp 950\u2013958. https:\/\/doi.org\/10.1145\/3292500.3330989","DOI":"10.1145\/3292500.3330989"},{"key":"6061_CR31","doi-asserted-by":"publisher","unstructured":"Zhou Y, Guo J, Sun H, Song B, Yu FR (2023) Attention-guided multi-step fusion: a hierarchical fusion network for multimodal recommendation. In: Proceedings of the 46th international acm sigir conference on research and development in information retrieval, pp 1816\u20131820. https:\/\/doi.org\/10.1145\/3539618.3591950","DOI":"10.1145\/3539618.3591950"},{"key":"6061_CR32","doi-asserted-by":"publisher","unstructured":"Jing L, Tian Y (2021) Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans Pattern Anal Mach Intell:4037\u20134058. https:\/\/doi.org\/10.1109\/TPAMI.2020.2992393","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"6061_CR33","doi-asserted-by":"publisher","unstructured":"Mahendran A, Thewlis J, Vedaldi A (2019) Cross pixel optical-flow similarity for self-supervised learning. In: Computer vision\u2013ACCV 2018: 14th asian conference on computer vision, pp 99\u2013116. https:\/\/doi.org\/10.1007\/978-3-030-20873-8_7","DOI":"10.1007\/978-3-030-20873-8_7"},{"key":"6061_CR34","doi-asserted-by":"publisher","unstructured":"Liu X, Zhang F, Hou Z, Mian L, Wang Z, Zhang J, Tang J (2021) Self-supervised learning: generative or contrastive. IEEE Trans Knowl Data Eng:857\u2013876. https:\/\/doi.org\/10.1109\/TKDE.2021.3090866","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"6061_CR35","unstructured":"Veli\u010dkovi\u0107 P, Fedus W, Hamilton WL, Li\u00f2 P, Bengio Y, Hjelm D (2019) Deep Graph Infomax. In: International conference on learning representations, p 4"},{"key":"6061_CR36","doi-asserted-by":"publisher","unstructured":"Wei W, Huang C, Xia L, Xu Y, Zhao J, Yin D (2022) Contrastive meta learning with behavior multiplicity for recommendation. In: Proceedings of the fifteenth acm international conference on web search and data mining, pp 1120\u20131128. https:\/\/doi.org\/10.1145\/3488560.3498527","DOI":"10.1145\/3488560.3498527"},{"key":"6061_CR37","doi-asserted-by":"publisher","unstructured":"He R, McAuley J (2016) Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering. In: Proceedings of the 25th international conference on world wide web, pp 507\u2013517. https:\/\/doi.org\/10.1145\/2872427.2883037","DOI":"10.1145\/2872427.2883037"},{"key":"6061_CR38","doi-asserted-by":"publisher","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp 3982\u20133992. https:\/\/doi.org\/10.18653\/v1\/D19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"6061_CR39","doi-asserted-by":"publisher","unstructured":"Chen J, Fang H-R, Saad Y (2009) Fast approximate KNN graph construction for high dimensional data via recursive Lanczos bisection. J Mach Learn Res:1989\u20132012. https:\/\/doi.org\/10.5555\/1577069.1755852","DOI":"10.5555\/1577069.1755852"},{"key":"6061_CR40","doi-asserted-by":"publisher","unstructured":"Wei Y, Wang X, Nie L, He X, Chua T-S (2020) Graph-refined convolutional network for multimedia recommendation with implicit feedback. In: Proceedings of the 28th ACM international conference on multimedia, pp 3541\u20133549. https:\/\/doi.org\/10.1145\/3394171.3413556","DOI":"10.1145\/3394171.3413556"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06061-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-06061-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06061-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T06:10:49Z","timestamp":1735798249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-06061-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6061"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-06061-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,18]]},"assertion":[{"value":"7 September 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest to this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}},{"value":"The datasets used for this experiment are publicly available by the respective organizations\/authors to further improve the Multimodal Recommendation research field. Thus, informed consent is not required to use the dataset. References and citations to relevant datasets are included in the manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"2"}}