{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T16:31:39Z","timestamp":1769013099776,"version":"3.49.0"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Displays"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1016\/j.displa.2023.102489","type":"journal-article","created":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T02:08:18Z","timestamp":1688609298000},"page":"102489","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":18,"special_numbering":"C","title":["RICH: A rapid method for image-text cross-modal hash retrieval"],"prefix":"10.1016","volume":"79","author":[{"given":"Bo","family":"Li","sequence":"first","affiliation":[]},{"given":"Dan","family":"Yao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5313-6134","authenticated-orcid":false,"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.displa.2023.102489_b1","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.ins.2020.08.009","article-title":"Drsl: Deep relational similarity learning for cross-modal retrieval","volume":"546","author":"Wang","year":"2021","journal-title":"Inform. Sci."},{"key":"10.1016\/j.displa.2023.102489_b2","doi-asserted-by":"crossref","unstructured":"J. Zhu, Z. Li, Y. Zeng, J. Wei, H. Ma, Image-Text Matching with Fine-Grained Relational Dependency and Bidirectional Attention-Based Generative Networks, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 395\u2013403.","DOI":"10.1145\/3503161.3548058"},{"key":"10.1016\/j.displa.2023.102489_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2023.102377","article-title":"Relational-convergent transformer for image captioning","volume":"77","author":"Chen","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.displa.2023.102489_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2022.102340","article-title":"Character-level arabic text generation from sign language video using encoder\u2013decoder model","volume":"76","author":"Boukdir","year":"2023","journal-title":"Displays"},{"key":"10.1016\/j.displa.2023.102489_b5","doi-asserted-by":"crossref","unstructured":"L. Ma, Z. Lu, L. Shang, H. Li, Multimodal convolutional neural networks for matching image and sentence, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 2623\u20132631.","DOI":"10.1109\/ICCV.2015.301"},{"key":"10.1016\/j.displa.2023.102489_b6","doi-asserted-by":"crossref","unstructured":"Y. Huang, Q. Wu, C. Song, L. Wang, Learning semantic concepts and order for image and sentence matching, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6163\u20136171.","DOI":"10.1109\/CVPR.2018.00645"},{"issue":"2","key":"10.1016\/j.displa.2023.102489_b7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3383184","article-title":"Dual-path convolutional image-text embedding with instance loss","volume":"16","author":"Zheng","year":"2020","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.displa.2023.102489_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2021.102082","article-title":"RAFNet: RGB-D attention feature fusion network for indoor semantic segmentation","volume":"70","author":"Yan","year":"2021","journal-title":"Displays"},{"key":"10.1016\/j.displa.2023.102489_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2022.102275","article-title":"Generic parallel data structures and algorithms to GPU superpixel image segmentation","volume":"74","author":"Mansouri","year":"2022","journal-title":"Displays"},{"issue":"6","key":"10.1016\/j.displa.2023.102489_b10","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.displa.2023.102489_b11","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"issue":"1","key":"10.1016\/j.displa.2023.102489_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103154","article-title":"Unifying knowledge iterative dissemination and relational reconstruction network for image\u2013text matching","volume":"60","author":"Xie","year":"2023","journal-title":"Inf. Process. Manage."},{"key":"10.1016\/j.displa.2023.102489_b13","doi-asserted-by":"crossref","unstructured":"L. Jing, E. Vahdani, J. Tan, Y. Tian, Cross-modal center loss for 3D cross-modal retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3142\u20133151.","DOI":"10.1109\/CVPR46437.2021.00316"},{"key":"10.1016\/j.displa.2023.102489_b14","doi-asserted-by":"crossref","unstructured":"T. Yu, Y. Yang, Y. Li, L. Liu, H. Fei, P. Li, Heterogeneous attention network for effective and efficient cross-modal retrieval, in: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021, pp. 1146\u20131156.","DOI":"10.1145\/3404835.3462924"},{"key":"10.1016\/j.displa.2023.102489_b15","doi-asserted-by":"crossref","unstructured":"K. Wang, L. Herranz, J. van de Weijer, Continual learning in cross-modal retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3628\u20133638.","DOI":"10.1109\/CVPRW53098.2021.00402"},{"key":"10.1016\/j.displa.2023.102489_b16","doi-asserted-by":"crossref","unstructured":"X. Lu, L. Zhu, Z. Cheng, J. Li, X. Nie, H. Zhang, Flexible online multi-modal hashing for large-scale multimedia retrieval, in: Proceedings of the 27th ACM International Conference on Multimedia, 2019, pp. 1129\u20131137.","DOI":"10.1145\/3343031.3350999"},{"key":"10.1016\/j.displa.2023.102489_b17","doi-asserted-by":"crossref","unstructured":"G. Wu, Z. Lin, J. Han, L. Liu, G. Ding, B. Zhang, J. Shen, Unsupervised Deep Hashing via Binary Latent Factor Models for Large-scale Cross-modal Retrieval, in: Proceedings of International Joint Conference on Artificial Intelligence, 2018, pp. 2854\u20132860.","DOI":"10.24963\/ijcai.2018\/396"},{"key":"10.1016\/j.displa.2023.102489_b18","doi-asserted-by":"crossref","unstructured":"S. Su, Z. Zhong, C. Zhang, Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 3027\u20133035.","DOI":"10.1109\/ICCV.2019.00312"},{"key":"10.1016\/j.displa.2023.102489_b19","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1109\/TMM.2021.3053766","article-title":"Aggregation-based graph convolutional hashing for unsupervised cross-modal retrieval","volume":"24","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.displa.2023.102489_b20","series-title":"Neural Networks: Tricks of the Trade","first-page":"55","article-title":"Early stopping-but when?","author":"Prechelt","year":"1998"},{"key":"10.1016\/j.displa.2023.102489_b21","unstructured":"S. Kumar, R. Udupa, Learning hash functions for cross-view similarity search, in: Proceedings of the 22nd International Joint Conference on Artificial Intelligence, 2011, pp. 1360\u20131365."},{"key":"10.1016\/j.displa.2023.102489_b22","doi-asserted-by":"crossref","unstructured":"J. Song, Y. Yang, Y. Yang, Z. Huang, H.T. Shen, Inter-media hashing for large-scale retrieval from heterogeneous data sources, in: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, 2013, pp. 785\u2013796.","DOI":"10.1145\/2463676.2465274"},{"key":"10.1016\/j.displa.2023.102489_b23","doi-asserted-by":"crossref","unstructured":"G. Ding, Y. Guo, J. Zhou, Collective matrix factorization hashing for multimodal data, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 2075\u20132082.","DOI":"10.1109\/CVPR.2014.267"},{"key":"10.1016\/j.displa.2023.102489_b24","doi-asserted-by":"crossref","unstructured":"C. Li, C. Deng, L. Wang, D. Xie, X. Liu, Coupled cyclegan: Unsupervised hashing network for cross-modal retrieval, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2019, pp. 176\u2013183.","DOI":"10.1609\/aaai.v33i01.3301176"},{"key":"10.1016\/j.displa.2023.102489_b25","doi-asserted-by":"crossref","unstructured":"S. Liu, S. Qian, Y. Guan, J. Zhan, L. Ying, Joint-modal distribution-based similarity hashing for large-scale unsupervised deep cross-modal retrieval, in: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020, pp. 1379\u20131388.","DOI":"10.1145\/3397271.3401086"},{"key":"10.1016\/j.displa.2023.102489_b26","first-page":"1","article-title":"Quadruplet-based deep cross-modal hashing","volume":"2021","author":"Liu","year":"2021","journal-title":"Comput. Intell. Neurosci."},{"key":"10.1016\/j.displa.2023.102489_b27","doi-asserted-by":"crossref","unstructured":"J. Qin, L. Fei, J. Zhu, J. Wen, C. Tian, S. Wu, Scalable Discriminative Discrete Hashing For Large-Scale Cross-Modal Retrieval, in: Proceedings of 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, 2021, pp. 4330\u20134334.","DOI":"10.1109\/ICASSP39728.2021.9413871"},{"key":"10.1016\/j.displa.2023.102489_b28","doi-asserted-by":"crossref","unstructured":"J. Yi, X. Liu, Y.m. Cheung, X. Xu, W. Fan, Y. He, Efficient online label consistent hashing for large-scale cross-modal retrieval, in: Proceedings of 2021 IEEE International Conference on Multimedia and Expo, 2021, pp. 1\u20136.","DOI":"10.1109\/ICME51207.2021.9428323"},{"key":"10.1016\/j.displa.2023.102489_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.106818","article-title":"NSDH: A nonlinear supervised discrete hashing framework for large-scale cross-modal retrieval","volume":"217","author":"Yang","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.displa.2023.102489_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107252","article-title":"Learning a maximized shared latent factor for cross-modal hashing","volume":"228","author":"Wang","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.displa.2023.102489_b31","doi-asserted-by":"crossref","unstructured":"X. Luo, Y. Wu, X.S. Xu, Scalable supervised discrete hashing for large-scale search, in: Proceedings of the 2018 World Wide Web Conference, 2018, pp. 1603\u20131612.","DOI":"10.1145\/3178876.3186072"},{"key":"10.1016\/j.displa.2023.102489_b32","doi-asserted-by":"crossref","unstructured":"Y. Wang, Z.D. Chen, X. Luo, X.-S. Xu, High-dimensional sparse cross-modal hashing with fine-grained similarity embedding, in: Proceedings of the 2021 Web Conference, 2021, pp. 2900\u20132909.","DOI":"10.1145\/3442381.3449798"},{"key":"10.1016\/j.displa.2023.102489_b33","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/j.neucom.2022.09.037","article-title":"Discrete asymmetric zero-shot hashing with application to cross-modal retrieval","volume":"511","author":"Shu","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.displa.2023.102489_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108262","article-title":"Discrete online cross-modal hashing","volume":"122","author":"Zhan","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.displa.2023.102489_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104475","article-title":"Matching images and texts with multi-head attention network for cross-media hashing retrieval","volume":"106","author":"Li","year":"2021","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.displa.2023.102489_b36","doi-asserted-by":"crossref","unstructured":"Y. Zhao, Y. Zhu, S. Liao, Q. Ye, H. Zhang, Class Concentration with Twin Variational Autoencoders for Unsupervised Cross-modal Hashing, in: Proceedings of the Asian Conference on Computer Vision, 2022, pp. 349\u2013365.","DOI":"10.1007\/978-3-031-26351-4_15"},{"key":"10.1016\/j.displa.2023.102489_b37","doi-asserted-by":"crossref","unstructured":"Y. Zhao, J. Yu, S. Liao, Z. Zhang, H. Zhang, From Sparse to Dense: Semantic Graph Evolutionary Hashing for Unsupervised Cross-Modal Retrieval, in: Proceedings of the Asian Conference on Computer Vision, 2022, pp. 195\u2013211.","DOI":"10.1007\/978-3-031-26316-3_31"},{"key":"10.1016\/j.displa.2023.102489_b38","doi-asserted-by":"crossref","unstructured":"C. Sun, H. Latapie, G. Liu, Y. Yan, Deep Normalized Cross-Modal Hashing with Bi-Direction Relation Reasoning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4941\u20134949.","DOI":"10.1109\/CVPRW56347.2022.00541"},{"key":"10.1016\/j.displa.2023.102489_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.106851","article-title":"Task-adaptive asymmetric deep cross-modal hashing","volume":"219","author":"Li","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.displa.2023.102489_b40","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.ins.2022.07.095","article-title":"Specific class center guided deep hashing for cross-modal retrieval","volume":"609","author":"Shu","year":"2022","journal-title":"Inform. Sci."},{"issue":"6","key":"10.1016\/j.displa.2023.102489_b41","first-page":"6461","article-title":"Watch: two-stage discrete cross-media hashing","volume":"35","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"9","key":"10.1016\/j.displa.2023.102489_b42","doi-asserted-by":"crossref","first-page":"6665","DOI":"10.1007\/s00521-022-08006-6","article-title":"Robust supervised matrix factorization hashing with application to cross-modal retrieval","volume":"35","author":"Shu","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.displa.2023.102489_b43","first-page":"1","article-title":"Modality-invariant asymmetric networks for cross-modal hashing","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.displa.2023.102489_b44","first-page":"3877","article-title":"Unsupervised contrastive cross-modal hashing","author":"Hu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.displa.2023.102489_b45","doi-asserted-by":"crossref","unstructured":"G. Huang, S. Liu, L. Van der Maaten, K.Q. Weinberger, Condensenet: An efficient densenet using learned group convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 2752\u20132761.","DOI":"10.1109\/CVPR.2018.00291"},{"key":"10.1016\/j.displa.2023.102489_b46","doi-asserted-by":"crossref","unstructured":"Y. Zhu, S. Newsam, Densenet for dense flow, in: Proceedings of IEEE International Conference on Image Processing, 2017, pp. 790\u2013794.","DOI":"10.1109\/ICIP.2017.8296389"},{"key":"10.1016\/j.displa.2023.102489_b47","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7","key":"10.1016\/j.displa.2023.102489_b48","doi-asserted-by":"crossref","first-page":"7670","DOI":"10.1007\/s10489-021-02804-6","article-title":"Unsupervised hash retrieval based on multiple similarity matrices and text self-attention mechanism","volume":"52","author":"Hou","year":"2022","journal-title":"Appl. Intell."},{"key":"10.1016\/j.displa.2023.102489_b49","doi-asserted-by":"crossref","unstructured":"M.J. Huiskes, M.S. Lew, The mir flickr retrieval evaluation, in: Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval, 2008, pp. 39\u201343.","DOI":"10.1145\/1460096.1460104"},{"key":"10.1016\/j.displa.2023.102489_b50","doi-asserted-by":"crossref","unstructured":"T.S. Chua, J. Tang, R. Hong, H. Li, Z. Luo, Y. Zheng, Nus-wide: a real-world web image database from national university of singapore, in: Proceedings of the ACM International Conference on Image and Video Retrieval, 2009, pp. 1\u20139.","DOI":"10.1145\/1646396.1646452"},{"issue":"3","key":"10.1016\/j.displa.2023.102489_b51","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1109\/TPAMI.2013.142","article-title":"On the role of correlation and abstraction in cross-modal multimedia retrieval","volume":"36","author":"Pereira","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.displa.2023.102489_b52","doi-asserted-by":"crossref","unstructured":"Z. Niu, M. Zhou, L. Wang, X. Gao, G. Hua, Hierarchical multimodal lstm for dense visual-semantic embedding, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1881\u20131889.","DOI":"10.1109\/ICCV.2017.208"},{"key":"10.1016\/j.displa.2023.102489_b53","doi-asserted-by":"crossref","unstructured":"X. Luo, X.Y. Yin, L. Nie, X. Song, Y. Wang, X.-S. Xu, et al., SDMCH: Supervised Discrete Manifold-Embedded Cross-Modal Hashing, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2018, pp. 2518\u20132524.","DOI":"10.24963\/ijcai.2018\/349"}],"container-title":["Displays"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938223001221?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938223001221?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T11:51:27Z","timestamp":1758887487000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0141938223001221"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":53,"alternative-id":["S0141938223001221"],"URL":"https:\/\/doi.org\/10.1016\/j.displa.2023.102489","relation":{},"ISSN":["0141-9382"],"issn-type":[{"value":"0141-9382","type":"print"}],"subject":[],"published":{"date-parts":[[2023,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RICH: A rapid method for image-text cross-modal hash retrieval","name":"articletitle","label":"Article Title"},{"value":"Displays","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.displa.2023.102489","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"102489"}}