{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T15:03:00Z","timestamp":1784732580295,"version":"3.55.0"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"8","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"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":"crossref","award":["62302338"],"award-info":[{"award-number":["62302338"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["ZR2025MS1067"],"award-info":[{"award-number":["ZR2025MS1067"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:p>\n                    Large-scale image retrieval increasingly depends on triplet-based deep hashing methods, which typically construct training triplets using class labels. However, existing triplet-based hashing methods relying on sparse and noisy categorical labels suffer from two main issues: no triplet, where sparse annotations limit valid triplet formation, and bad triplet, where noisy or ambiguous labels cause misleading samples, which together hinder the network from learning a well-structured similarity space, causing semantically similar images to scatter and dissimilar ones to collapse, ultimately undermining retrieval accuracy. In this article, we solve this dilemma with a novel unified deep hashing framework, termed Deep Relational Knowledge Distillation Hashing (DRKDH), which decouples semantic relation modeling from visual feature learning by leveraging a teacher-student paradigm to learn semantically consistent hash codes. Specifically, the teacher model captures comprehensive semantic structural relationships across all instances, providing information-rich and noise-resilient supervision to guide the student model in learning expressive and discriminative visual embeddings, effectively mitigating the impact of low-quality triplet labels. Furthermore, by leveraging similarity weights predicted by the teacher model, a relaxed masking triplet loss is introduced into the student model, which dynamically adjusts the contribution of each triplet based on its informativeness, suppressing invalid or misleading triplets while emphasizing valuable ones to enhance training efficiency. Comprehensive experiments on THINGS, ImageNet, MIRFLICKR-25K, and NUS-WIDE show that DRKDH consistently outperforms state-of-the-art deep hashing methods under sparse and noisy supervision, while additional evaluations suggest competitive performance in selected zero-shot and few-shot settings. Source codes:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/QinLab-WFU\/DRKDH\">https:\/\/github.com\/QinLab-WFU\/DRKDH<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3820061","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T13:07:44Z","timestamp":1781269664000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Relational Knowledge Distillation Hashing via Relaxed Masking Triplet Optimization for Large-scale Image Retrieval"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1592-9325","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Qufu Normal University, Rizhao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7976-318X","authenticated-orcid":false,"given":"Qibing","family":"Qin","sequence":"additional","affiliation":[{"name":"Weifang University, Weifang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7459-2510","authenticated-orcid":false,"given":"Wenfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4087-3677","authenticated-orcid":false,"given":"Lei","family":"Huang","sequence":"additional","affiliation":[{"name":"Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"677","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Brown Andrew","year":"2020","unstructured":"Andrew Brown, Weidi Xie, Vicky Kalogeiton, and Andrew Zisserman. 2020. Smooth-AP: Smoothing the path towards large-scale image retrieval. In Proceedings of the European Conference on Computer Vision. Springer, 677\u2013694."},{"key":"e_1_3_2_3_2","first-page":"5608","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Cao Z.","year":"2017","unstructured":"Z. Cao, M. Long, J. Wang, and P. S. Yu. 2017. HashNet: Deep learning to hash by continuation. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 5608\u20135617."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3749983"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2026.3654452"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_8_2","first-page":"1181","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Dondera Radu","year":"2024","unstructured":"Radu Dondera. 2024. Towards learning image similarity from general triplet labels. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1181\u20131190."},{"key":"e_1_3_2_9_2","first-page":"7758","volume-title":"IEEE Transactions on Multimedia","volume":"25","author":"Fu Zheren","year":"2022","unstructured":"Zheren Fu, Zhendong Mao, Bo Hu, An-An Liu, and Yongdong Zhang. 2022. Intra-class adaptive augmentation with neighbor correction for deep metric learning. IEEE Transactions on Multimedia 25 (2022), 7758\u20137771."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3785478"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-020-00951-3"},{"key":"e_1_3_2_13_2","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00319"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285266"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3401050"},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","first-page":"109799","DOI":"10.1016\/j.compeleceng.2024.109799","article-title":"A gradual approach to knowledge distillation in deep supervised hashing for large-scale image retrieval","volume":"120","author":"Hussain Abid","year":"2024","unstructured":"Abid Hussain, Heng-Chao Li, Mehboob Hussain, Muqadar Ali, Shaheen Abbas, Danish Ali, and Amir Rehman. 2024. A gradual approach to knowledge distillation in deep supervised hashing for large-scale image retrieval. Computers and Electrical Engineering 120 (2024), 109799.","journal-title":"Computers and Electrical Engineering"},{"issue":"4","key":"e_1_3_2_19_2","first-page":"1","article-title":"Deep supervised hashing with multiscale object-driven knowledge distillation for image retrieval","volume":"14","author":"Hussain Abid","year":"2025","unstructured":"Abid Hussain, Heng-Chao Li, Muqadar Ali, Mehboob Hussain, Ali Choo, Danish Ali, and Amir Rehman. 2025. Deep supervised hashing with multiscale object-driven knowledge distillation for image retrieval. International Journal of Multimedia Information Retrieval 14, 4 (2025), 1\u201321.","journal-title":"International Journal of Multimedia Information Retrieval"},{"key":"e_1_3_2_20_2","first-page":"354","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Jang Young Kyun","year":"2022","unstructured":"Young Kyun Jang, Geonmo Gu, Byungsoo Ko, Isaac Kang, and Nam Ik Cho. 2022. Deep hash distillation for image retrieval. In Proceedings of the European Conference on Computer Vision. Springer, 354\u2013371."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298947"},{"key":"e_1_3_2_23_2","first-page":"4779","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"39","author":"Li Jiaxing","year":"2025","unstructured":"Jiaxing Li, Lin Jiang, Zeqi Ma, Kaihang Jiang, Xiaozhao Fang, and Jie Wen. 2025. Lightweight contrastive distilled hashing for online cross-modal retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 4779\u20134787."},{"key":"e_1_3_2_24_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"30","author":"Li Qi","year":"2017","unstructured":"Qi Li, Zhenan Sun, Ran He, and Tieniu Tan. 2017. Deep supervised discrete hashing. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_2_25_2","unstructured":"Wu-Jun Li Sheng Wang and Wang-Cheng Kang. 2015. Feature learning based deep supervised hashing with pairwise labels. arXiv:1511.03855. Retrieved from https:\/\/arxiv.org\/abs\/1511.03855"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.227"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33326"},{"key":"e_1_3_2_28_2","first-page":"526","volume-title":"IEEE Transactions on Neural Networks and Learning Systems","volume":"37","author":"Liu Lei","year":"2025","unstructured":"Lei Liu, Yunji Liang, Xiaokai Yan, Luwen Huangfu, Sagar Samtani, Zhiwen Yu, Yanyong Zhang, and Daniel D. Zeng. 2025. Hard sample mining: A new paradigm of efficient and robust model training. IEEE Transactions on Neural Networks and Learning Systems 37, 2 (2025), 526\u2013546."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2678163"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.237"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02288-0"},{"key":"e_1_3_2_34_2","first-page":"130014","volume-title":"Neurocomputing","volume":"635","author":"Qin Qibing","year":"2025","unstructured":"Qibing Qin, Hong Wang, Wenfeng Zhang, Lei Huang, and Jie Nie. 2025. Deep consistent penalizing hashing with noise-robust representation for large-scale image retrieval. Neurocomputing 635 (2025), 130014."},{"key":"e_1_3_2_35_2","first-page":"1881","volume-title":"IEEE Transactions on Multimedia","volume":"26","author":"Qin Qibing","year":"2023","unstructured":"Qibing Qin, Kezhen Xie, Wenfeng Zhang, Chengduan Wang, and Lei Huang. 2023. Deep neighborhood structure-preserving hashing for large-scale image retrieval. IEEE Transactions on Multimedia 26 (2023), 1881\u20131893."},{"key":"e_1_3_2_36_2","unstructured":"Adriana Romero Nicolas Ballas Samira Ebrahimi Kahou Antoine Chassang Carlo Gatta and Yoshua Bengio. 2014. FitNets: Hints for thin deep nets. arXiv:1412.6550. Retrieved from https:\/\/arxiv.org\/abs\/1412.6550"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"issue":"10","key":"e_1_3_2_38_2","doi-asserted-by":"crossref","first-page":"6729","DOI":"10.1007\/s11263-025-02506-3","article-title":"An empirical study on training paradigms for deep supervised hashing: Y. Shen et al","volume":"133","author":"Shen Yang","year":"2025","unstructured":"Yang Shen, Peng Wang, Xiu-Shen Wei, and Yazhou Yao. 2025. An empirical study on training paradigms for deep supervised hashing: Y. Shen et al. International Journal of Computer Vision 133, 10 (2025), 6729\u20136767.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-025-02770-2"},{"issue":"2","key":"e_1_3_2_40_2","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/s13735-024-00326-8","article-title":"Unsupervised graph reasoning distillation hashing for multimodal hamming space search with vision-language model","volume":"13","author":"Sun Lina","year":"2024","unstructured":"Lina Sun and Yumin Dong. 2024. Unsupervised graph reasoning distillation hashing for multimodal hamming space search with vision-language model. International Journal of Multimedia Information Retrieval 13, 2 (2024), 16.","journal-title":"International Journal of Multimedia Information Retrieval"},{"key":"e_1_3_2_41_2","unstructured":"Yonglong Tian Dilip Krishnan and Phillip Isola. 2019. Contrastive representation distillation. arXiv:1910.10699. Retrieved from https:\/\/arxiv.org\/abs\/1910.10699"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02246"},{"key":"e_1_3_2_44_2","first-page":"70","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Wang Xiaofang","year":"2016","unstructured":"Xiaofang Wang, Yi Shi, and Kris M. Kitani. 2016. Deep supervised hashing with triplet labels. In Proceedings of the Asian Conference on Computer Vision. Springer, 70\u201384."},{"key":"e_1_3_2_45_2","article-title":"Supervised hashing for image retrieval via image representation learning","volume":"28","author":"Xia Rongkai","year":"2014","unstructured":"Rongkai Xia, Yan Pan, Hanjiang Lai, Cong Liu, and Shuicheng Yan. 2014. Supervised hashing for image retrieval via image representation learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 28.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_46_2","first-page":"10665","volume-title":"IEEE Transactions on Multimedia","volume":"26","author":"Xiang Xinguang","year":"2024","unstructured":"Xinguang Xiang, Xinhao Ding, Lu Jin, Zechao Li, Jinhui Tang, and Ramesh Jain. 2024. Alleviating over-fitting in hashing-based fine-grained image retrieval: From causal feature learning to binary-injected hash learning. IEEE Transactions on Multimedia 26 (2024), 10665\u201310677."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548032"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00659"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00315"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929957"},{"key":"e_1_3_2_51_2","first-page":"1556","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhao Fang","year":"2015","unstructured":"Fang Zhao, Yongzhen Huang, Liang Wang, and Tieniu Tan. 2015. Deep semantic ranking based hashing for multi-label image retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1556\u20131564."},{"key":"e_1_3_2_52_2","article-title":"Deep hashing network for efficient similarity retrieval","volume":"30","author":"Zhu Han","year":"2016","unstructured":"Han Zhu, Mingsheng Long, Jianmin Wang, and Yue Cao. 2016. Deep hashing network for efficient similarity retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 30.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043298"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3820061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T14:26:47Z","timestamp":1784730407000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3820061"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":52,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,31]]}},"alternative-id":["10.1145\/3820061"],"URL":"https:\/\/doi.org\/10.1145\/3820061","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"assertion":[{"value":"2026-01-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}