{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:50:07Z","timestamp":1777571407535,"version":"3.51.4"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2021,10,7]],"date-time":"2021-10-07T00:00:00Z","timestamp":1633564800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,7]],"date-time":"2021-10-07T00:00:00Z","timestamp":1633564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61966004"],"award-info":[{"award-number":["61966004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Natural Natural Science Foundation","award":["2019GXNSFDA245018"],"award-info":[{"award-number":["2019GXNSFDA245018"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s10489-021-02804-6","type":"journal-article","created":{"date-parts":[[2021,10,7]],"date-time":"2021-10-07T07:17:58Z","timestamp":1633591078000},"page":"7670-7685","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Unsupervised hash retrieval based on multiple similarity matrices and text self-attention mechanism"],"prefix":"10.1007","volume":"52","author":[{"given":"Chuanwen","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5313-6134","authenticated-orcid":false,"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingli","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,7]]},"reference":[{"key":"2804_CR1","doi-asserted-by":"crossref","unstructured":"Gu J, Cai J, Joty SR, Niu L, Wang G (2018) Look, imagine and match: Improving textual-visual cross-modal retrieval with generative models. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 7181\u20137189","DOI":"10.1109\/CVPR.2018.00750"},{"key":"2804_CR2","doi-asserted-by":"crossref","unstructured":"Li K, Zhang Y, Li K, Li Y, Fu Y (2019) Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 4654\u20134662","DOI":"10.1109\/ICCV.2019.00475"},{"key":"2804_CR3","doi-asserted-by":"crossref","unstructured":"Ji Z, Wang H, Han J, Pang Y (2019) Saliency-guided attention network for image-sentence matching. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 5754\u20135763","DOI":"10.1109\/ICCV.2019.00585"},{"key":"2804_CR4","doi-asserted-by":"crossref","unstructured":"Wang S, Wang R, Yao Z, Shan S, Chen X (2020) Cross-modal scene graph matching for relationship-aware image-text retrieval. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision. pp 1508\u20131517","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"2804_CR5","doi-asserted-by":"crossref","unstructured":"Eisenschtat A, Wolf L (2017) Linking image and text with 2-way nets. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4601\u20134611","DOI":"10.1109\/CVPR.2017.201"},{"issue":"2","key":"2804_CR6","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang L, Li Y, Huang J, Lazebnik S (2018) Learning two-branch neural networks for image-text matching tasks. IEEE Trans Pattern Anal Mach Intell 41(2):394\u2013407","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2804_CR7","doi-asserted-by":"crossref","unstructured":"Liu Y, Guo Y, Bakker EM, Lew MS (2017) Learning a recurrent residual fusion network for multimodal matching. In: Proceedings of the IEEE international conference on computer vision. pp 4107\u20134116","DOI":"10.1109\/ICCV.2017.442"},{"issue":"7","key":"2804_CR8","doi-asserted-by":"publisher","first-page":"3490","DOI":"10.1109\/TIP.2019.2897944","volume":"28","author":"Q-Y Jiang","year":"2019","unstructured":"Jiang Q-Y, Li W-J (2019) Discrete latent factor model for cross-modal hashing. IEEE Trans Image Process 28(7):3490\u2013 3501","journal-title":"IEEE Trans Image Process"},{"key":"2804_CR9","doi-asserted-by":"crossref","unstructured":"Wu D, Dai Q, Liu J, Li B, Wang W (2019) Deep incremental hashing network for efficient image retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 9069\u20139077","DOI":"10.1109\/CVPR.2019.00928"},{"key":"2804_CR10","doi-asserted-by":"crossref","unstructured":"Wu D, Liu J, Li B, Wang W (2018) Deep index-compatible hashing for fast image retrieval. In: 2018 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1\u20136","DOI":"10.1109\/ICME.2018.8486463"},{"key":"2804_CR11","doi-asserted-by":"crossref","unstructured":"Lu X, Zhu L, Cheng Z, Li J, Nie X, Zhang H (2019) Flexible online multi-modal hashing for large-scale multimedia retrieval. In: Proceedings of the 27th ACM international conference on multimedia. pp 1129\u20131137","DOI":"10.1145\/3343031.3350999"},{"key":"2804_CR12","doi-asserted-by":"crossref","unstructured":"Lu X, Zhu L, Cheng Z, Nie L, Zhang H (2019) Online multi-modal hashing with dynamic query-adaption. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval. pp 715\u2013724","DOI":"10.1145\/3331184.3331217"},{"key":"2804_CR13","doi-asserted-by":"crossref","unstructured":"Sun C, Song X, Feng F, Xin Zhao W, Zhang H, Nie L (2019) Supervised hierarchical cross-modal hashing. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval. pp 725\u2013734","DOI":"10.1145\/3331184.3331229"},{"key":"2804_CR14","doi-asserted-by":"crossref","unstructured":"Long M, Cao Y, Wang J, Yu PS (2016) Composite correlation quantization for efficient multimodal retrieval. In: Proceedings of the 39th international ACM SIGIR conference on research and development in information retrieval. pp 579\u2013588","DOI":"10.1145\/2911451.2911493"},{"key":"2804_CR15","doi-asserted-by":"crossref","unstructured":"Liong VE, Lu J, Tan Y-P, Zhou J (2017) Cross-modal deep variational hashing. In: Proceedings of the IEEE international conference on computer vision. pp 4077\u20134085","DOI":"10.1109\/ICCV.2017.439"},{"key":"2804_CR16","doi-asserted-by":"crossref","unstructured":"Yang E, Liu T, Deng C, Liu W, Tao D (2019) Distillhash: Unsupervised deep hashing by distilling data pairs. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 2946\u20132955","DOI":"10.1109\/CVPR.2019.00306"},{"key":"2804_CR17","doi-asserted-by":"crossref","unstructured":"Gu W, Gu X, Gu J, Li B, Xiong Z, Wang W (2019) Adversary guided asymmetric hashing for cross-modal retrieval. In: Proceedings of the 2019 on international conference on multimedia retrieval. pp 159\u2013167","DOI":"10.1145\/3323873.3325045"},{"key":"2804_CR18","doi-asserted-by":"crossref","unstructured":"Wang B, Yang Y, Xu X, Hanjalic A, Shen HT (2017) Adversarial cross-modal retrieval. In: Proceedings of the 25th ACM international conference on Multimedia. pp 154\u2013162","DOI":"10.1145\/3123266.3123326"},{"key":"2804_CR19","doi-asserted-by":"crossref","unstructured":"Ye Z, Peng Y (2018) Multi-scale correlation for sequential cross-modal hashing learning. In: Proceedings of the 26th ACM international conference on Multimedia. pp 852\u2013860","DOI":"10.1145\/3240508.3240560"},{"key":"2804_CR20","doi-asserted-by":"crossref","unstructured":"Li C, Deng C, Wang L, De X, Liu X (2019) Coupled cyclegan: Unsupervised hashing network for cross-modal retrieval. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 176\u2013183","DOI":"10.1609\/aaai.v33i01.3301176"},{"key":"2804_CR21","doi-asserted-by":"crossref","unstructured":"Wang W, Shen Y, Zhang H, Yao Y, Liu L (2020) Set and rebase: determining the semantic graph connectivity for unsupervised cross modal hashing. In: International joint conference on artificial intelligence. pp 853\u2013859","DOI":"10.24963\/ijcai.2020\/119"},{"key":"2804_CR22","doi-asserted-by":"crossref","unstructured":"Yang D, Wu D, Zhang W, Zhang H, Li B, Wang W (2020) Deep semantic-alignment hashing for unsupervised cross-modal retrieval. In: Proceedings of the 2020 international conference on multimedia retrieval. pp 44\u201352","DOI":"10.1145\/3372278.3390673"},{"key":"2804_CR23","doi-asserted-by":"crossref","unstructured":"Su S, Zhong Z, Zhang C (2019) Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 3027\u20133035","DOI":"10.1109\/ICCV.2019.00312"},{"key":"2804_CR24","doi-asserted-by":"crossref","unstructured":"Liu S, Qian S, Guan Y, Zhan J, Ying L (2020) 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. pp 1379\u20131388","DOI":"10.1145\/3397271.3401086"},{"key":"2804_CR25","doi-asserted-by":"crossref","unstructured":"Wang D, Wang Q, An Y, Gao X, Tian Y (2020) Online collective matrix factorization hashing for large-scale cross-media retrieval. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval. pp 1409\u20131418","DOI":"10.1145\/3397271.3401132"},{"key":"2804_CR26","doi-asserted-by":"crossref","unstructured":"Wu G, Lin Z, Han J, Liu L, Ding G, Zhang B, Shen J (2018) Unsupervised deep hashing via binary latent factor models for large-scale cross-modal retrieval. In: IJCAI. pp 2854\u20132860","DOI":"10.24963\/ijcai.2018\/396"},{"key":"2804_CR27","doi-asserted-by":"crossref","unstructured":"Zhang J, Peng Y, Yuan M (2018) Unsupervised generative adversarial cross-modal hashing. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11263"},{"key":"2804_CR28","unstructured":"Kumar S, Udupa R (2011) Learning hash functions for cross-view similarity search. In: Twenty-second international joint conference on artificial intelligence"},{"key":"2804_CR29","doi-asserted-by":"crossref","unstructured":"Song J, Yang Y, Yang Y, Huang Z, Shen HT (2013) Inter-media hashing for large-scale retrieval from heterogeneous data sources. In: Proceedings of the 2013 ACM SIGMOD international conference on management of Data. pp 785\u2013796","DOI":"10.1145\/2463676.2465274"},{"key":"2804_CR30","doi-asserted-by":"crossref","unstructured":"Ding G, Guo Y, Zhou J (2014) Collective matrix factorization hashing for multimodal data. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 2075\u20132082","DOI":"10.1109\/CVPR.2014.267"},{"key":"2804_CR31","unstructured":"Wu B, Yang Q, Zheng W-S, Wang Y, Wang J (2015) Quantized correlation hashing for fast cross-modal search. In: IJCAI. Citeseer, pp 3946\u20133952"},{"issue":"4","key":"2804_CR32","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TMM.2018.2866771","volume":"21","author":"D Hu","year":"2018","unstructured":"Hu D, Nie F, Li X (2018) Deep binary reconstruction for cross-modal hashing. IEEE Trans Multimed 21(4):973\u2013985","journal-title":"IEEE Trans Multimed"},{"key":"2804_CR33","doi-asserted-by":"crossref","unstructured":"Liu X, Yu G, Domeniconi C, Wang J, Ren Y, Guo M (2019) Ranking-based deep cross-modal hashing. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 4400\u20134407","DOI":"10.1609\/aaai.v33i01.33014400"},{"key":"2804_CR34","doi-asserted-by":"crossref","unstructured":"Li C, Deng C, Li N, Liu W, Gao X, Tao D (2018) Self-supervised adversarial hashing networks for cross-modal retrieval. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4242\u20134251","DOI":"10.1109\/CVPR.2018.00446"},{"key":"2804_CR35","doi-asserted-by":"crossref","unstructured":"Jiang Q-Y, Li W-J (2017) Deep cross-modal hashing. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 3232\u20133240","DOI":"10.1109\/CVPR.2017.348"},{"key":"2804_CR36","doi-asserted-by":"publisher","first-page":"3626","DOI":"10.1109\/TIP.2020.2963957","volume":"29","author":"X De","year":"2020","unstructured":"De X, Deng C, Li C, Liu X, Tao D (2020) Multi-task consistency-preserving adversarial hashing for cross-modal retrieval. IEEE Trans Image Process 29:3626\u20133637","journal-title":"IEEE Trans Image Process"},{"key":"2804_CR37","doi-asserted-by":"crossref","unstructured":"Hu H, Xie L, Hong R, Tian Q (2020) Creating something from nothing: Unsupervised knowledge distillation for cross-modal hashing. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 3123\u20133132","DOI":"10.1109\/CVPR42600.2020.00319"},{"key":"2804_CR38","doi-asserted-by":"crossref","unstructured":"Xu R, Li C, Yan J, Deng C, Liu X (2019) Graph convolutional network hashing for cross-modal retrieval. In: Ijcai. pp 982\u2013988","DOI":"10.24963\/ijcai.2019\/138"},{"key":"2804_CR39","doi-asserted-by":"crossref","unstructured":"Cao Y, Liu B, Long M, Wang J (2018) Cross-modal hamming hashing. In: Proceedings of the European conference on computer vision (ECCV). pp 202\u2013218","DOI":"10.1007\/978-3-030-01246-5_13"},{"key":"2804_CR40","doi-asserted-by":"crossref","unstructured":"Tan Z, Wang M, Xie J, Chen Y, Shi X (2018) Deep semantic role labeling with self-attention. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11928"},{"key":"2804_CR41","doi-asserted-by":"crossref","unstructured":"Zhou W, Yuan J, Lei J, Luo T (2020) Tsnet: three-stream self-attention network for rgb-d indoor semantic segmentation. IEEE Intell Syst","DOI":"10.1109\/MIS.2020.2999462"},{"key":"2804_CR42","doi-asserted-by":"crossref","unstructured":"Zhou W, Liu W, Lei J, Luo T, Yu L (2021) Deep binocular fixation prediction using a hierarchical multimodal fusion network. IEEE Trans Cognit Develop Syst","DOI":"10.1109\/TCDS.2021.3051010"},{"key":"2804_CR43","doi-asserted-by":"crossref","unstructured":"Zhou W, Guo Q, Lei J, Yu L, Hwang Jenq-Neng (2021) Ecffnet: effective and consistent feature fusion network for rgb-t salient object detection. IEEE Trans Circ Syst Vid Technol","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"2804_CR44","doi-asserted-by":"crossref","unstructured":"Zhou W, Zhu Y, Lei J, Wan J, Yu L (2021) Ccafnet: crossflow and cross-scale adaptive fusion network for detecting salient objects in rgb-d images. IEEE Trans Multimed","DOI":"10.1109\/TETCI.2021.3097393"},{"key":"2804_CR45","doi-asserted-by":"crossref","unstructured":"Cao Z, Long M, Wang J, Yu PS (2017) Hashnet: Deep learning to hash by continuation. In: Proceedings of the IEEE international conference on computer vision. pp 5608\u20135617","DOI":"10.1109\/ICCV.2017.598"},{"issue":"3","key":"2804_CR46","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1109\/TPAMI.2013.142","volume":"36","author":"JC Pereira","year":"2013","unstructured":"Pereira JC, Coviello E, Doyle G, Rasiwasia N, Lanckriet GRG, Levy R, Vasconcelos N (2013) On the role of correlation and abstraction in cross-modal multimedia retrieval. IEEE Trans Pattern Anal Mach Intell 36(3):521\u2013535","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2804_CR47","doi-asserted-by":"crossref","unstructured":"Huiskes MJ, Lew MS (2008) The mir flickr retrieval evaluation. In: Proceedings of the 1st ACM international conference on Multimedia information retrieval. pp 39\u201343","DOI":"10.1145\/1460096.1460104"},{"key":"2804_CR48","doi-asserted-by":"crossref","unstructured":"Chua T-S, Tang J, Hong R, Li H, Luo Z, Zheng Y (2009) 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. pp 1\u20139","DOI":"10.1145\/1646396.1646452"},{"key":"2804_CR49","doi-asserted-by":"crossref","unstructured":"Zhang P-F, Li Y, Huang Z, Xu X-S (2021) Aggregation-based graph convolutional hashing for unsupervised cross-modal retrieval. IEEE Trans Multimed","DOI":"10.1109\/TMM.2021.3053766"},{"key":"2804_CR50","doi-asserted-by":"crossref","unstructured":"Wang Y, Chen Z-D, Luo X, Li R, Xu X-S (2021) Fast cross-modal hashing with global and local similarity embedding. IEEE Trans Cybern","DOI":"10.1109\/TCYB.2021.3059886"},{"key":"2804_CR51","doi-asserted-by":"publisher","first-page":"106818","DOI":"10.1016\/j.knosys.2021.106818","volume":"217","author":"Z Yang","year":"2021","unstructured":"Yang Z, Yang L, Raymond OI, Zhu L, Huang W, Liao Z, Long J (2021) Nsdh: A nonlinear supervised discrete hashing framework for large-scale cross-modal retrieval. Knowl-Based Syst 217:106818","journal-title":"Knowl-Based Syst"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02804-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02804-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02804-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T08:05:17Z","timestamp":1673424317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02804-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,7]]},"references-count":51,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["2804"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02804-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,7]]},"assertion":[{"value":"25 August 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work. There is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}