{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:19:41Z","timestamp":1783153181358,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","funder":[{"name":"Shandong Provincial Natural Science Foundation","award":["ZR2022MF333"],"award-info":[{"award-number":["ZR2022MF333"]}]},{"name":"the Key Laboratory of Computing Power Network and Information Security, Ministry of Educationunder","award":["2023ZD028"],"award-info":[{"award-number":["2023ZD028"]}]},{"name":"the Sci-Tech Innovation 2030—“New Generation Artificial Intelligence” Major Project","award":["2018AAA0102100"],"award-info":[{"award-number":["2018AAA0102100"]}]},{"name":"the Natural Science Foundation of Liaoning Province","award":["2021-MS-261"],"award-info":[{"award-number":["2021-MS-261"]}]},{"name":"the Key Project of the Natural Science Foundation of Zhejiang Province","award":["LZ22F020014"],"award-info":[{"award-number":["LZ22F020014"]}]},{"name":"the Key R&D Sub-Project of the Ministry of Science and Technology","award":["2021YFF0307505"],"award-info":[{"award-number":["2021YFF0307505"]}]},{"name":"the Liaoning Provincial Project","award":["XLYC2203002"],"award-info":[{"award-number":["XLYC2203002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792526","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"2263-2272","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HL-CMR: Hypergraph Learning for Cross-Modal Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9548-7701","authenticated-orcid":false,"given":"Guohui","family":"Ding","sequence":"first","affiliation":[{"name":"Shenyang Aerospace University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4886-1549","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9019-4560","authenticated-orcid":false,"given":"Yimin","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6807-4362","authenticated-orcid":false,"given":"Rui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Swinburne University of Technology, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3174970"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Y. Bai Z. Shu J. Yu Z. Yu and X. Wu. 2023. Proxy-based graph convolutional hashing for cross-modal retrieval. IEEE Transactions on Big Data (2023) 371-385.","DOI":"10.1109\/TBDATA.2023.3338951"},{"key":"e_1_3_2_1_3_1","unstructured":"D. Busbridge D. Sherburn P. Cavallo and N. Y. Hammerla. 2021. Relational graph attention networks. arXiv preprint arXiv:1904.05811."},{"key":"e_1_3_2_1_4_1","volume-title":"UNITER: Learning Universal Image-Text Representations. In European conference on computer vision (ECCV). https:\/\/arxiv.org\/abs\/1909","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. UNITER: Learning Universal Image-Text Representations. In European conference on computer vision (ECCV). https:\/\/arxiv.org\/abs\/1909.11740"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_6_1","first-page":"145","article-title":"Large Scale Hypergraph Computation. In Hypergraph Computation. Springer Nature Singapore","author":"Dai Q.","year":"2023","unstructured":"Q. Dai and Y. Gao. 2023. Large Scale Hypergraph Computation. In Hypergraph Computation. Springer Nature Singapore, Singapore, 145-157.","journal-title":"Singapore"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence. 3890-3896","author":"Di W.","unstructured":"W. Di, X. Gao, X. Wang, and L. He. 2015. Semantic topic multimodal hashing for cross-media retrieval. In Proceedings of the International Joint Conference on Artificial Intelligence. 3890-3896."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186005X47697"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.267"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075242"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108676"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.09401"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"e_1_3_2_1_14_1","first-page":"3877","article-title":"Unsupervised contrastive cross-modal hashing","volume":"45","author":"Hu Peng","year":"2022","unstructured":"Peng Hu, Hongyuan Zhu, Jie Lin, Dezhong Peng, Yin-Ping Zhao, and Xi Peng. 2022. Unsupervised contrastive cross-modal hashing. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 3 (2022), 3877-3889.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval. 39-43","author":"Mark","unstructured":"Mark J. Huiskes and Michael S. Lew. 2008. The MIR Flickr Retrieval Evaluation. In Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval. 39-43."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285266"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-023-00952-6"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR). 1-14","author":"Kipf T. N.","unstructured":"T. N. Kipf and M. Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR). 1-14."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 11th ACM International Conference on Multimedia. 604-611","author":"Li D.","unstructured":"D. Li, N. Dimitrova, M. Li, and I.K. Sethi. 2003. Multimedia content processing through cross-modal association. In Proceedings of the 11th ACM International Conference on Multimedia. 604-611."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"F. Li B. Wang L. Zhu J. Li Z. Zhang and X. Chang. 2025. Cross-domain transfer hashing for efficient cross-modal retrieval. IEEE Transactions on Circuits and Systems for Video Technology (2025). doi:10.1109\/TCSVT.2024.3374791","DOI":"10.1109\/TCSVT.2024.3374791"},{"key":"e_1_3_2_1_22_1","volume-title":"Hoi","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Pan Lu, Chunyuan Xiong, and Steven C.H. Hoi. 2021. ALBEF: Align before fuse vision and language representation learning. In Advances in Neural Information Processing Systems (NeurIPS). https:\/\/arxiv.org\/abs\/2107.07651"},{"key":"e_1_3_2_1_23_1","volume-title":"A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide. arXiv preprint arXiv:2404.01039","author":"Li Ruoyu","year":"2024","unstructured":"Ruoyu Li, Weixi Zhu, Mingkai Fan, Pan Zhou, and Yisen Wang. 2024. A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide. arXiv preprint arXiv:2404.01039 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the European Conference on Computer Vision. 740-755","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Proceedings of the European Conference on Computer Vision. 740-755."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3864-3872","author":"Lin Z.","unstructured":"Z. Lin, G. Ding, M. Hu, and J. Wang. 2015. Semantics-preserving hashing for cross-view retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3864-3872."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254199"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254199"},{"key":"e_1_3_2_1_28_1","first-page":"45","article-title":"Learning Multi-semantic Based on Cross-Attention for Image-Text Retrieval. In Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data. Springer Nature Singapore","author":"Lu B.","year":"2024","unstructured":"B. Lu, Y. Gao, T. Zhao, X. Yuan, H. Zhu, L. Gan, and X. Duan. 2024. Learning Multi-semantic Based on Cross-Attention for Image-Text Retrieval. In Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data. Springer Nature Singapore, Singapore, 45-56.","journal-title":"Singapore"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969792"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0078"},{"key":"e_1_3_2_1_31_1","volume-title":"Semantic disentanglement adversarial hashing for cross-modal retrieval","author":"Meng Min","year":"2023","unstructured":"Min Meng, Jiaxuan Sun, Jigang Liu, Jun Yu, and Jigang Wu. 2023. Semantic disentanglement adversarial hashing for cross-modal retrieval. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3101642"},{"key":"e_1_3_2_1_33_1","first-page":"2440","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Qian S.","unstructured":"S. Qian, D. Xue, H. Zhang, Q. Fang, and C. Xu. 2021b. Dual adversarial graph neural networks for multi-label cross-modal retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 2440-2447."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3349075"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the ACM International Conference on Multimedia.","author":"X. S., Y. C., X.","year":"2024","unstructured":"X. S., Y. C., X. Y., and Y. Z., 2024. Graph convolutional semi-supervised cross-modal hashing. In Proceedings of the ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2160-2167","author":"Sharma A.","unstructured":"A. Sharma, A. Kumar, H. Daume, and D.W. Jacobs. 2012. Generalized multiview analysis: A discriminative latent space. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2160-2167."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2970050"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"X. Shen Y. Chen W. Liu Y. Zheng Q. Sun and S. Pan. 2024. Graph convolutional multi-label hashing for cross-modal retrieval. IEEE Transactions on Neural Networks and Learning Systems (2024) 1-13.","DOI":"10.2139\/ssrn.5071394"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177901"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the Pacific Rim Conference on Multimedia. Springer International Publishing, Cham, 776-786","author":"Tang D.","unstructured":"D. Tang, H. Cui, D. Shi, and H. Ji. 2018. Hypergraph-based discrete hashing learning for cross-modal retrieval. In Proceedings of the Pacific Rim Conference on Multimedia. Springer International Publishing, Cham, 776-786."},{"key":"e_1_3_2_1_41_1","first-page":"6798","article-title":"Deep cross-modal proxy hashing","volume":"35","author":"Tu R.","year":"2022","unstructured":"R. Tu, X. Mao, R. Tu, B. Bian, C. Cai, H. Wang, W. Wei, and H. Huang. 2022. Deep cross-modal proxy hashing. IEEE Transactions on Knowledge and Data Engineering, Vol. 35 (2022), 6798-6810.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591660"},{"key":"e_1_3_2_1_43_1","unstructured":"P. Velickovic G. Cucurull A. Casanova A. Romero P. Li\u00f2 and Y. Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the ACM International Conference on Multimedia. 154-162","author":"Wang B.","unstructured":"B. Wang, Y. Yang, X. Xu, A. Hanjalic, and H. T. Shen. 2017. Adversarial cross-modal retrieval. In Proceedings of the ACM International Conference on Multimedia. 154-162."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00277"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2974825"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413971"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101968"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). 982-988","author":"Xu R.","unstructured":"R. Xu, C. Li, J. Yan, C. Deng, and X. Liu. 2019. Graph convolutional network hashing for cross-modal retrieval. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). 982-988."},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 1618-1625","author":"Yang E.","unstructured":"E. Yang, C. Deng, W. Liu, X. Liu, D. Tao, and X. Gao. 2017. Pairwise relationship guided deep hashing for cross-modal retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence. 1618-1625."},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV). 28-36","author":"Yao T.","unstructured":"T. Yao, T. Mei, and C. Ngo. 2015. Learning query and image similarities with ranking canonical correlation analysis. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 28-36."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2215-2224","author":"Zeng Y.","unstructured":"Y. Zeng, D. Cao, X. Wei, M. Liu, Z. Zhao, and Z. Qin. 2021. Multi-modal relational graph for cross-modal video moment retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2215-2224."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276704"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3282894"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3053766"},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 10394-10403","author":"Zhen L.","unstructured":"L. Zhen, P. Hu, X. Wang, and D. Peng. 2019. Deep supervised cross-modal retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 10394-10403."},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the 31st ACM International Conference on Multimedia. ACM, 3517-3527","author":"Zhong F.","unstructured":"F. Zhong, C. Chu, Z. Zhu, and Z. Chen. 2023. Hypergraph-enhanced hashing for unsupervised cross-modal retrieval via robust similarity guidance. In Proceedings of the 31st ACM International Conference on Multimedia. ACM, 3517-3527."},{"key":"e_1_3_2_1_58_1","volume-title":"Information Fusion","volume":"121","author":"Zhu Jie","year":"2025","unstructured":"Jie Zhu, Dan Wang, Guangtian Shi, and Shufang Wu. 2025. Multi-label guided graph similarity learning for cross-modal retrieval. Information Fusion, Vol. 121 (2025), Article 103142."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121279"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:00:53Z","timestamp":1783152053000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792526"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":59,"alternative-id":["10.1145\/3774904.3792526","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792526","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}