{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:55:29Z","timestamp":1791910529305,"version":"4.3.4"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62372054, 62006005"],"award-info":[{"award-number":["62372054, 62006005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2022YFC3302200"],"award-info":[{"award-number":["2022YFC3302200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>\n            Deep hashing presents an effective strategy for large-scale image retrieval. Current hashing methods are generally categorized by their supervision types: point-wise, pairwise, and list-wise. Recent advancements in point-wise methods (e.g., CSQ, MDS) have significantly enhanced retrieval performance across diverse datasets by pre-assigning a hash center to each class, thereby improving the discriminability of the resultant hash codes. However, these methods employ purely data-independent algorithms for generating hash centers, overlooking the semantic connections between different classes, which, we argue, could degrade retrieval performance. To tackle this problem, this article expands on the newly emerged concept of \u201chash centers\u201d to introduce \u201c\n            <jats:italic toggle=\"yes\">semantic<\/jats:italic>\n            hash centers,\u201d which posits that hash centers of semantically related classes should exhibit closer Hamming distances, while those of unrelated classes should be more distant.\n          <\/jats:p>\n          <jats:p>\n            Based on this hypothesis, we propose a three-stage framework, termed Semantic Hash Centers (SHC), to produce hash codes that preserve semantics. First, we build a classification network to detect semantic similarities between classes, and utilize a data-dependent approach to similarity calculation that can adapt to varied data distributions. Next, we develop a new optimization algorithm to generate SHC. This algorithm not only maintains semantic relatedness among hash centers but also integrates a constraint to ensure a minimum distance between them, addressing the issue of excessively proximate hash centers potentially impairing retrieval performance. Finally, we train a deep hashing network with the above generated SHC to convert each image into a binary hash code. Experiments on large-scale image retrieval across several public datasets demonstrate that SHC generates more discriminative hash codes, markedly enhancing retrieval performance. Specifically, in terms of the mAP@100, mAP@1000, and mAP@ALL metrics, SHC records average improvements of +6.24%, +6.68%, and +10.39%, respectively, over the most competitive existing methods. The code of our SHC project is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/cc752424640\/Deep-Hashing-with-Semantic-Hash-Centers-for-Image-Retrieval\">https:\/\/github.com\/cc752424640\/Deep-Hashing-with-Semantic-Hash-Centers-for-Image-Retrieval<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3749983","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T16:55:01Z","timestamp":1753289701000},"page":"1-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep Hashing with Semantic Hash Centers for Image Retrieval"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7662-4912","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1373-6108","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4124-4151","authenticated-orcid":false,"given":"Yuxiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-3350","authenticated-orcid":false,"given":"Xudong","family":"Ma","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1348-9218","authenticated-orcid":false,"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8774-3725","authenticated-orcid":false,"given":"Dell","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973365"},{"key":"e_1_3_2_3_2","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. In NeurIPS."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1137\/17M1141394"},{"key":"e_1_3_2_5_2","first-page":"1229","article-title":"Deep Cauchy hashing for hamming space retrieval","author":"Cao Yue","year":"2018","unstructured":"Yue Cao, Mingsheng Long, Bin Liu, and Jianmin Wang. 2018. Deep Cauchy hashing for hamming space retrieval. In CVPR, 1229\u20131237.","journal-title":"CVPR"},{"key":"e_1_3_2_6_2","first-page":"5608","article-title":"HashNet: Deep learning to hash by continuation","author":"Cao Zhangjie","year":"2017","unstructured":"Zhangjie Cao, Mingsheng Long, Jianmin Wang, and Philip S. Yu. 2017. HashNet: Deep learning to hash by continuation. In ICCV, 5608\u20135617.","journal-title":"ICCV"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462888"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Yong Chen Zhibao Tian Hui Zhang Jun Wang and Dell Zhang. 2020. Strongly constrained discrete hashing. IEEE Trans. Image Process. 29 (2020) 3596\u20133611.","DOI":"10.1109\/TIP.2020.2963952"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2995195"},{"key":"e_1_3_2_10_2","unstructured":"Woocheol Choi and Jimyeong Kim. 2023. On the convergence analysis of the decentralized projected gradient descent. arXiv:2303.08412. Retrieved from https:\/\/arxiv.org\/abs\/2303.08412"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"e_1_3_2_12_2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT, 4171\u20134186.","journal-title":"NAACL-HLT"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.193"},{"key":"e_1_3_2_14_2","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR, 770\u2013778.","journal-title":"CVPR"},{"issue":"4","key":"e_1_3_2_15_2","first-page":"91:1","article-title":"An efficient and robust semantic hashing framework for similar text search","volume":"41","author":"He Liyang","year":"2023","unstructured":"Liyang He, Zhenya Huang, Enhong Chen, Qi Liu, Shiwei Tong, Hao Wang, Defu Lian, and Shijin Wang. 2023. An efficient and robust semantic hashing framework for similar text search. ACM Trans. Inf. Syst. 41, 4 (2023), 91:1\u201391:31.","journal-title":"ACM Trans. Inf. Syst"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681496"},{"key":"e_1_3_2_17_2","first-page":"24286","article-title":"One loss for all: Deep hashing with a single cosine similarity based learning objective","author":"Tian Hoe Jiun","year":"2021","unstructured":"Jiun Tian Hoe, Kam Woh Ng, Tianyu Zhang, Chee Seng Chan, Yi-Zhe Song, and Tao Xiang. 2021. One loss for all: Deep hashing with a single cosine similarity based learning objective. In NeurIPS, 24286\u201324298.","journal-title":"NeurIPS"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_2_19_2","first-page":"354","volume-title":"ECCVLecture Notes in Computer Science","volume":"13674","author":"Kyun Jang Young","year":"2022","unstructured":"Young Kyun Jang, Geonmo Gu, ByungSoo Ko, Isaac Kang, and Nam Ik Cho. 2022. Deep hash distillation for image retrieval. In ECCV. Shai Avidan, Gabriel J. Brostow, Moustapha Ciss\u00e9, Giovanni Maria Farinella, and Tal Hassner (Eds.), Lecture Notes in Computer Science, Vol. 13674, Springer, 354\u2013371."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_21_2","first-page":"3342","article-title":"Asymmetric deep supervised hashing","author":"Jiang Qing-Yuan","year":"2018","unstructured":"Qing-Yuan Jiang and Wu-Jun Li. 2018. Asymmetric deep supervised hashing. In AAAI, 3342\u20133349.","journal-title":"AAAI"},{"key":"e_1_3_2_22_2","first-page":"554","article-title":"3D object representations for fine-grained categorization","author":"Krause Jonathan","year":"2013","unstructured":"Jonathan Krause, Michael Stark, Jia Deng, and Li Fei-Fei. 2013. 3D object representations for fine-grained categorization. In ICCV, 554\u2013561.","journal-title":"ICCV"},{"key":"e_1_3_2_23_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report University of Toronto."},{"key":"e_1_3_2_24_2","first-page":"2130","article-title":"Kernelized locality-sensitive hashing for scalable image search","author":"Kulis Brian","year":"2009","unstructured":"Brian Kulis and Kristen Grauman. 2009. Kernelized locality-sensitive hashing for scalable image search. In ICCV, 2130\u20132137.","journal-title":"ICCV"},{"key":"e_1_3_2_25_2","first-page":"3270","article-title":"Simultaneous feature learning and hash coding with deep neural networks","author":"Lai Hanjiang","year":"2015","unstructured":"Hanjiang Lai, Yan Pan, Ye Liu, and Shuicheng Yan. 2015. Simultaneous feature learning and hash coding with deep neural networks. In CVPR, 3270\u20133278.","journal-title":"CVPR"},{"key":"e_1_3_2_26_2","first-page":"1711","volume-title":"IJCAI","author":"Li Wu-Jun","year":"2016","unstructured":"Wu-Jun Li, Sheng Wang, and Wang-Cheng Kang. 2016. Feature learning based deep supervised hashing with pairwise labels. In IJCAI. Subbarao Kambhampati (Ed.), IJCAI\/AAAI Press, 1711\u20131717."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254199"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331217"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532624"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Leland McInnes and John Healy. 2018. UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426. Retrieved from https:\/\/arxiv.org\/abs\/1802.03426","DOI":"10.21105\/joss.00861"},{"key":"e_1_3_2_32_2","first-page":"1070","article-title":"Hamming distance metric learning","author":"Norouzi Mohammad","year":"2012","unstructured":"Mohammad Norouzi, David J. Fleet, and Russ R. Salakhutdinov. 2012. Hamming distance metric learning. In NeurIPS, 1070\u20131078.","journal-title":"NeurIPS"},{"key":"e_1_3_2_33_2","first-page":"10","article-title":"Binary cross entropy with deep learning technique for image classification","volume":"9","author":"Ruby Usha","year":"2020","unstructured":"Usha Ruby and Vamsidhar Yendapalli. 2020. Binary cross entropy with deep learning technique for image classification. Int. J. Adv. Trends Comput. Sci. Eng. 9 (2020), 10.","journal-title":"Int. J. Adv. Trends Comput. Sci. Eng"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_2_35_2","unstructured":"Shupeng Su Chao Zhang Kai Han and Yonghong Tian. 2018. Greedy hash: Towards fast optimization for accurate hash coding in CNN. In IJCAI 806\u2013815."},{"key":"e_1_3_2_36_2","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy Christian","year":"2015","unstructured":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR, 1\u20139.","journal-title":"CVPR"},{"key":"e_1_3_2_37_2","first-page":"595","article-title":"Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection","author":"Van Horn Grant","year":"2015","unstructured":"Grant Van Horn, Steve Branson, Ryan Farrell, Scott Haber, Jessie Barry, Panos Ipeirotis, Pietro Perona, and Serge Belongie. 2015. Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection. In CVPR, 595\u2013604.","journal-title":"CVPR"},{"key":"e_1_3_2_38_2","first-page":"739","article-title":"Estimate of the number of signals in error correcting codes","volume":"117","author":"Varshamov Rom Rubenovich","year":"1957","unstructured":"Rom Rubenovich Varshamov. 1957. Estimate of the number of signals in error correcting codes. Docklady Akad. Nauk, SSSR 117 (1957), 739\u2013741.","journal-title":"Docklady Akad. Nauk, SSSR"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2487976"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"e_1_3_2_41_2","first-page":"23455","article-title":"Deep hashing with minimal-distance-separated hash centers","author":"Wang Liangdao","year":"2023","unstructured":"Liangdao Wang, Yan Pan, Cong Liu, Hanjiang Lai, Jian Yin, and Ye Liu. 2023. Deep hashing with minimal-distance-separated hash centers. In CVPR, 23455\u201323464.","journal-title":"CVPR"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650205"},{"key":"e_1_3_2_43_2","first-page":"70","article-title":"Deep supervised hashing with triplet labels","author":"Wang Xiaofang","year":"2017","unstructured":"Xiaofang Wang, Yi Shi, and Kris M. Kitani. 2017. Deep supervised hashing with triplet labels. In ACCV, 70\u201384.","journal-title":"ACCV"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8952"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Xingming Xiao Shu Cao Liejun Wang Shuli Cheng and Erdong Yuan. 2024. Deep hashing image retrieval based on hybrid neural network and optimized metric learning. Knowl.-Based Syst. 284 (2024) 111336.","DOI":"10.1016\/j.knosys.2023.111336"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248170"},{"key":"e_1_3_2_47_2","first-page":"2946","article-title":"Distillhash: Unsupervised deep hashing by distilling data pairs","author":"Yang Erkun","year":"2019","unstructured":"Erkun Yang, Tongliang Liu, Cheng Deng, Wei Liu, and Dacheng Tao. 2019. Distillhash: Unsupervised deep hashing by distilling data pairs. In CVPR, 2946\u20132955.","journal-title":"CVPR"},{"key":"e_1_3_2_48_2","first-page":"3931","article-title":"Deep semantic-preserving and ranking-based hashing for image retrieval","author":"Yao Ting","year":"2016","unstructured":"Ting Yao, Fuchen Long, Tao Mei, and Yong Rui. 2016. Deep semantic-preserving and ranking-based hashing for image retrieval. In IJCAI, 3931\u20133937.","journal-title":"IJCAI"},{"key":"e_1_3_2_49_2","first-page":"3083","article-title":"Central similarity quantization for efficient image and video retrieval","author":"Yuan Li","year":"2020","unstructured":"Li Yuan, Tao Wang, Xiaopeng Zhang, Francis E. H. Tay, Zequn Jie, Wei Liu, and Jiashi Feng. 2020. Central similarity quantization for efficient image and video retrieval. In CVPR, 3083\u20133092.","journal-title":"CVPR"},{"key":"e_1_3_2_50_2","first-page":"1318","article-title":"Binary neural network hashing for image retrieval","author":"Zhang Wanqian","year":"2021","unstructured":"Wanqian Zhang, Dayan Wu, Yu Zhou, Bo Li, Weiping Wang, and Dan Meng. 2021. Binary neural network hashing for image retrieval. In SIGIR, 1318\u20131327.","journal-title":"SIGIR"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929957"},{"key":"e_1_3_2_52_2","first-page":"1556","article-title":"Deep semantic ranking based hashing for multi-label image retrieval","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 CVPR, 1556\u20131564.","journal-title":"CVPR"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Han Zhu Mingsheng Long Jianmin Wang and Yue Cao. 2016. Deep hashing network for efficient similarity retrieval. In AAAI Vol. 30.","DOI":"10.1609\/aaai.v30i1.10235"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3749983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:57:07Z","timestamp":1757624227000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3749983"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3749983"],"URL":"https:\/\/doi.org\/10.1145\/3749983","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"assertion":[{"value":"2024-11-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}