{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:54:12Z","timestamp":1774220052741,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11760-026-05240-6","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:02:49Z","timestamp":1773169369000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HNAF: Hard Negative Sample Mining and Adaptive Fusion for Multi-modal Recommendation"],"prefix":"10.1007","volume":"20","author":[{"given":"Weidong","family":"Kong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panxing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"issue":"5","key":"5240_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3535101","volume":"55","author":"S Wu","year":"2022","unstructured":"Wu, S., Sun, F., Zhang, W., Xie, X., Cui, B.: Graph neural networks in recommender systems: a survey. ACM Comput. Surv. 55(5), 1\u201337 (2022)","journal-title":"ACM Comput. Surv."},{"key":"5240_CR2","doi-asserted-by":"crossref","unstructured":"Ma, Y., Liu, X., Wei, Y., Tao, Z., Wang, X., Chua, T.-S.: Leveraging multimodal features and item-level user feedback for bundle construction. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pp. 510\u2013519 (2024)","DOI":"10.1145\/3616855.3635854"},{"key":"5240_CR3","doi-asserted-by":"crossref","unstructured":"Kim, Y., Kim, T., Shin, W.-Y., Kim, S.-W.: Monet: Modality-embracing graph convolutional network and target-aware attention for multimedia recommendation. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pp. 332\u2013340 (2024)","DOI":"10.1145\/3616855.3635817"},{"key":"5240_CR4","doi-asserted-by":"crossref","unstructured":"He, R., McAuley, J.: Vbpr: visual bayesian personalized ranking from implicit feedback. In: Proceedings of the AAAI Conference on Artificial Intelligence, 30 (2016)","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"5240_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wu, S., Wang, L.: Deepstyle: Learning user preferences for visual recommendation. In: Proceedings of the 40th International Acm Sigir Conference on Research and Development in Information Retrieval, pp. 841\u2013844 (2017)","DOI":"10.1145\/3077136.3080658"},{"key":"5240_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108616","volume":"246","author":"L Chen","year":"2022","unstructured":"Chen, L., Xie, T., Li, J., Zheng, Z.: Graph enhanced neural interaction model for recommendation. Knowl.-Based Syst. 246, 108616 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"5240_CR7","unstructured":"Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A., Bengio, Y.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"5240_CR8","doi-asserted-by":"crossref","unstructured":"Smith, B., Linden, G.: Two decades of recommender systems at amazon. com. Ieee internet computing 21(3), 12\u201318 (2017)","DOI":"10.1109\/MIC.2017.72"},{"issue":"9","key":"5240_CR9","doi-asserted-by":"publisher","first-page":"9154","DOI":"10.1109\/TKDE.2022.3221949","volume":"35","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Zhu, Y., Liu, Q., Zhang, M., Wu, S., Wang, L.: Latent structure mining with contrastive modality fusion for multimedia recommendation. IEEE Trans. Knowl. Data Eng. 35(9), 9154\u20139167 (2022)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"5240_CR10","doi-asserted-by":"crossref","unstructured":"Zhou, X., Shen, Z.: A tale of two graphs: Freezing and denoising graph structures for multimodal recommendation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 935\u2013943 (2023)","DOI":"10.1145\/3581783.3611943"},{"key":"5240_CR11","doi-asserted-by":"crossref","unstructured":"Yu, P., Tan, Z., Lu, G., Bao, B.-K.: Multi-view graph convolutional network for multimedia recommendation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6576\u20136585 (2023)","DOI":"10.1145\/3581783.3613915"},{"key":"5240_CR12","doi-asserted-by":"crossref","unstructured":"Luo, X., Cao, J., Sun, T., Yu, J., Huang, R., Yuan, W., Lin, H., Zheng, Y., Wang, S., Hu, Q., et al. Qarm: Quantitative alignment multi-modal recommendation at kuaishou. In: Proceedings of the 34th ACM International Conference on Information and Knowledge Management, pp. 5915\u20135922 (2025)","DOI":"10.1145\/3746252.3761502"},{"key":"5240_CR13","doi-asserted-by":"crossref","unstructured":"Cui, X., Lu, W., Tong, Y., Li, Y., Zhao, Z.: Multi-modal multi-behavior sequential recommendation with conditional diffusion-based feature denoising. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1593\u20131602 (2025)","DOI":"10.1145\/3726302.3730044"},{"key":"5240_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, J., Wang, C., Liu, Z., Zhu, X., Lin, C.: Cross: Feedback-oriented multi-modal dynamic alignment in recommendation systems. ACM Transactions on Recommender Systems (2025)","DOI":"10.1145\/3734527"},{"key":"5240_CR15","unstructured":"Zhang, Q., Wei, Y., Han, Z., Fu, H., Peng, X., Deng, C., Hu, Q., Xu, C., Wen, J., Hu, D., et al.: Multimodal fusion on low-quality data: A comprehensive survey. arXiv preprint arXiv:2404.18947 (2024)"},{"key":"5240_CR16","unstructured":"Zhou, H., Zhou, X., Zeng, Z., Zhang, L., Shen, Z.: A comprehensive survey on multimodal recommender systems: Taxonomy, evaluation, and future directions. arXiv preprint arXiv:2302.04473 (2023)"},{"key":"5240_CR17","unstructured":"Xia, J., Wu, L., Wang, G., Chen, J., Li, S.Z.: Progcl: Rethinking hard negative mining in graph contrastive learning. arXiv preprint arXiv:2110.02027 (2021)"},{"key":"5240_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"5240_CR19","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"5240_CR20","doi-asserted-by":"crossref","unstructured":"Xu, J., Chen, Z., Yang, S., Li, J., Wang, W., Hu, X., Hoi, S., Ngai, E.: A survey on multimodal recommender systems: Recent advances and future directions. arXiv preprint arXiv:2502.15711 (2025)","DOI":"10.1109\/TMM.2026.3668620"},{"key":"5240_CR21","doi-asserted-by":"crossref","unstructured":"Mao, K., Zhu, J., Xiao, X., Lu, B., Wang, Z., He, X.: Ultragcn: ultra simplification of graph convolutional networks for recommendation. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 1253\u20131262 (2021)","DOI":"10.1145\/3459637.3482291"},{"key":"5240_CR22","unstructured":"Pei, H., Wei, B., Chang, K.C.-C., Lei, Y., Yang, B.: Geom-gcn: Geometric graph convolutional networks. arXiv preprint arXiv:2002.05287 (2020)"},{"key":"5240_CR23","first-page":"21798","volume":"33","author":"Y Kalantidis","year":"2020","unstructured":"Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 21798\u201321809 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5240_CR24","doi-asserted-by":"crossref","unstructured":"Ong, R.K., Khong, A.W.: Spectrum-based modality representation fusion graph convolutional network for multimodal recommendation. In: Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, pp. 773\u2013781 (2025)","DOI":"10.1145\/3701551.3703561"},{"key":"5240_CR25","unstructured":"Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: Bpr: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012)"},{"key":"5240_CR26","doi-asserted-by":"crossref","unstructured":"He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: 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 (2020)","DOI":"10.1145\/3397271.3401063"},{"key":"5240_CR27","doi-asserted-by":"crossref","unstructured":"Wei, Y., Wang, X., Nie, L., He, X., Hong, R., Chua, T.-S.: 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 (2019)","DOI":"10.1145\/3343031.3351034"},{"key":"5240_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhou, H., Liu, Y., Zeng, Z., Miao, C., Wang, P., You, Y., Jiang, F.: Bootstrap latent representations for multi-modal recommendation. In: Proceedings of the ACM Web Conference 2023, pp. 845\u2013854 (2023)","DOI":"10.1145\/3543507.3583251"},{"key":"5240_CR29","doi-asserted-by":"publisher","first-page":"8454","DOI":"10.1609\/aaai.v38i8.28688","volume":"38","author":"Z Guo","year":"2024","unstructured":"Guo, Z., Li, J., Li, G., Wang, C., Shi, S., Ruan, B.: Lgmrec: Local and global graph learning for multimodal recommendation. Proceedings of the AAAI Conference on Artificial Intelligence 38, 8454\u20138462 (2024)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"5240_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Xia, L., Wei, W., Luo, D., Lin, K., Huang, C.: Diffmm: Multi-modal diffusion model for recommendation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 7591\u20137599 (2024)","DOI":"10.1145\/3664647.3681498"},{"key":"5240_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, X.: Mmrec: Simplifying multimodal recommendation. In: Proceedings of the 5th ACM International Conference on Multimedia in Asia Workshops, pp. 1\u20132 (2023)","DOI":"10.1145\/3611380.3628561"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05240-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05240-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05240-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:15:32Z","timestamp":1774217732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05240-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["5240"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05240-6","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"26 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":4,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"155"}}