{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T18:28:42Z","timestamp":1769020122199,"version":"3.49.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,1,20]],"date-time":"2021-01-20T00:00:00Z","timestamp":1611100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,20]],"date-time":"2021-01-20T00:00:00Z","timestamp":1611100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s10489-020-02137-w","type":"journal-article","created":{"date-parts":[[2021,1,20]],"date-time":"2021-01-20T03:02:36Z","timestamp":1611111756000},"page":"5927-5939","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Multi-attention based semantic deep hashing for cross-modal retrieval"],"prefix":"10.1007","volume":"51","author":[{"given":"Liping","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Gangyi","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Bingyao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wenjie","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Chengyang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,20]]},"reference":[{"key":"2137_CR1","doi-asserted-by":"crossref","unstructured":"Andoni A, Indyk P (2006) Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In: 2006 47th annual IEEE symposium on foundations of computer science (FOCS\u201906). IEEE, pp 459\u2013468","DOI":"10.1109\/FOCS.2006.49"},{"key":"2137_CR2","doi-asserted-by":"crossref","unstructured":"Kulis B, Grauman K (2009) Kernelized locality-sensitive hashing for scalable image search. In: ICCV, vol 9, pp 2130\u20132137","DOI":"10.1109\/ICCV.2009.5459466"},{"key":"2137_CR3","doi-asserted-by":"crossref","unstructured":"Wang J, Kumar S, Chang S-F (2010) Semi-supervised hashing for scalable image retrieval","DOI":"10.1109\/CVPR.2010.5539994"},{"issue":"12","key":"2137_CR4","doi-asserted-by":"publisher","first-page":"2916","DOI":"10.1109\/TPAMI.2012.193","volume":"35","author":"Y Gong","year":"2012","unstructured":"Gong Y, Lazebnik S, Gordo A, Perronnin F (2012) Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans Pattern Anal Mach Intell 35 (12):2916\u20132929","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2137_CR5","unstructured":"Kong W, Li W-J (2012) Isotropic hashing. In: Advances in neural information processing systems, pp 1646\u20131654"},{"key":"2137_CR6","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":"2137_CR7","doi-asserted-by":"crossref","unstructured":"Lin Z, Ding G, Hu M, Wang J (2015) Semantics-preserving hashing for cross-view retrieval. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3864\u20133872","DOI":"10.1109\/CVPR.2015.7299011"},{"key":"2137_CR8","doi-asserted-by":"crossref","unstructured":"Cao Y, Long M, Wang J, Yang Q, Yu P S (2016) Deep visual-semantic hashing for cross-modal retrieval. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, pp 1445\u20131454","DOI":"10.1145\/2939672.2939812"},{"key":"2137_CR9","doi-asserted-by":"crossref","unstructured":"Carreira-Perpin\u00e1n M A, Raziperchikolaei R (2015) Hashing with binary autoencoders. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 557\u2013566","DOI":"10.1109\/CVPR.2015.7298654"},{"key":"2137_CR10","doi-asserted-by":"crossref","unstructured":"Cao Y, Long M, Wang J, Zhu H (2016) Correlation autoencoder hashing for supervised cross-modal search. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval. ACM, pp 197\u2013204","DOI":"10.1145\/2911996.2912000"},{"issue":"6","key":"2137_CR11","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1109\/TIP.2016.2545300","volume":"25","author":"H Lai","year":"2016","unstructured":"Lai H, Yan P, Shu X, Wei Y, Yan S (2016) Instance-aware hashing for multi-label image retrieval. IEEE Trans Image Process 25(6):2469\u20132479","journal-title":"IEEE Trans Image Process"},{"issue":"4","key":"2137_CR12","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"},{"issue":"5","key":"2137_CR13","doi-asserted-by":"publisher","first-page":"2494","DOI":"10.1109\/TIP.2017.2676345","volume":"26","author":"X Xu","year":"2017","unstructured":"Xu X, Shen F, Yang Y, Shen H T, Li X (2017) Learning discriminative binary codes for large-scale cross-modal retrieval. IEEE Trans Image Process 26(5):2494\u20132507","journal-title":"IEEE Trans Image Process"},{"key":"2137_CR14","doi-asserted-by":"crossref","unstructured":"Zhang X, Lai H, Feng J (2018) Attention-aware deep adversarial hashing for cross-modal retrieval. In: Proceedings of the European Conference on Computer Vision (ECCV, pp 591\u2013606","DOI":"10.1007\/978-3-030-01267-0_36"},{"key":"2137_CR15","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.patrec.2019.08.032","volume":"128","author":"H Peng","year":"2019","unstructured":"Peng H, He J, Chen S, Wang Y, Qiao Y (2019) Dual-supervised attention network for deep cross-modal hashing. Pattern Recogn Lett 128:333\u2013339","journal-title":"Pattern Recogn Lett"},{"key":"2137_CR16","doi-asserted-by":"publisher","first-page":"14278","DOI":"10.1109\/ACCESS.2020.2966220","volume":"8","author":"G Xu","year":"2020","unstructured":"Xu G, Li X, Zhang Z (2020) Semantic consistency cross-modal retrieval with semi-supervised graph regularization. IEEE Access 8:14278\u201314288","journal-title":"IEEE Access"},{"key":"2137_CR17","doi-asserted-by":"crossref","unstructured":"Zhen L, Hu P, Wang X, Peng D (2019) Deep supervised cross-modal retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 10394\u201310403","DOI":"10.1109\/CVPR.2019.01064"},{"key":"2137_CR18","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2137_CR19","doi-asserted-by":"crossref","unstructured":"Bronstein M M, Bronstein A M, Michel F, Paragios N (2010) Data fusion through cross-modality metric learning using similarity-sensitive hashing. In: 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, pp 3594\u20133601","DOI":"10.1109\/CVPR.2010.5539928"},{"key":"2137_CR20","unstructured":"Kumar S, Udupa R (2011) Learning hash functions for cross-view similarity search. In: Twenty-Second International Joint Conference on Artificial Intelligence"},{"key":"2137_CR21","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"},{"issue":"7553","key":"2137_CR22","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"2137_CR23","doi-asserted-by":"crossref","unstructured":"Yang E, Deng C, Liu W, Liu X, Tao D, Gao X (2017) Pairwise relationship guided deep hashing for cross-modal retrieval. In: Thirty-First AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"2137_CR24","doi-asserted-by":"crossref","unstructured":"Song J, Yang Y, Yang Y, Huang Z, Shen H T (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. ACM, pp 785\u2013 796","DOI":"10.1145\/2463676.2465274"},{"key":"2137_CR25","unstructured":"Andrew G, Arora R, Bilmes J, Livescu K (2013) Deep canonical correlation analysis. In: International conference on machine learning, pp 1247\u20131255"},{"key":"2137_CR26","doi-asserted-by":"crossref","unstructured":"Liong V E, Lu J, Tan Y-P, Zhou J (2017) Cross-modal deep variational hashing. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, pp 4097\u20134105","DOI":"10.1109\/ICCV.2017.439"},{"key":"2137_CR27","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.neucom.2019.01.040","volume":"337","author":"C Yan","year":"2019","unstructured":"Yan C, Bai X, Wang S, Zhou J, Hancock E R (2019) Cross-modal hashing with semantic deep embedding. Neurocomputing 337:58\u201366","journal-title":"Neurocomputing"},{"key":"2137_CR28","doi-asserted-by":"crossref","unstructured":"Luo X, Yin X-Y, Nie L, Song X, Wang Y, Xu X-S (2018) Sdmch: Supervised discrete manifold-embedded cross-modal hashing. In: IJCAI, pp 2518\u20132524","DOI":"10.24963\/ijcai.2018\/349"},{"key":"2137_CR29","doi-asserted-by":"crossref","unstructured":"Hu D (2019) An introductory survey on attention mechanisms in nlp problems. In: Proceedings of SAI Intelligent Systems Conference. Springer, pp 432\u2013448","DOI":"10.1007\/978-3-030-29513-4_31"},{"key":"2137_CR30","unstructured":"Mnih V, Heess N, Graves A, et al. (2014) Recurrent models of visual attention. In: Advances in neural information processing systems, pp 2204\u20132212"},{"key":"2137_CR31","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning, pp 2048\u20132057"},{"key":"2137_CR32","doi-asserted-by":"crossref","unstructured":"Luong M-T, Pham H, Manning C D (2015) Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp 1412\u20131421","DOI":"10.18653\/v1\/D15-1166"},{"key":"2137_CR33","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2137_CR34","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations"},{"key":"2137_CR35","doi-asserted-by":"crossref","unstructured":"Fei-Fei L, Perona P (2005) A bayesian hierarchical model for learning natural scene categories. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol 2. IEEE, p 524\u2013531","DOI":"10.1109\/CVPR.2005.16"},{"key":"2137_CR36","unstructured":"Krizhevsky A, Sutskever I, Hinton G E (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"2137_CR37","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. ACM, pp 48","DOI":"10.1145\/1646396.1646452"},{"issue":"4","key":"2137_CR38","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.cviu.2009.03.008","volume":"114","author":"HJ Escalante","year":"2010","unstructured":"Escalante H J, Hern\u00e1ndez C A, Gonzalez J A, L\u00f3pez-L\u00f3pez A, Montes M, Morales E F, Sucar L E, Villase\u00f1or L, Grubinger M (2010) The segmented and annotated iapr tc-12 benchmark. Comput Vis Image Understand 114(4):419\u2013428","journal-title":"Comput Vis Image Understand"},{"key":"2137_CR39","doi-asserted-by":"crossref","unstructured":"Huiskes M J, Lew M S (2008) The mir flickr retrieval evaluation. In: Proceedings of the 1st ACM international conference on Multimedia information retrieval. ACM, pp 39\u201343","DOI":"10.1145\/1460096.1460104"},{"key":"2137_CR40","unstructured":"Liu W, Mu C, Kumar S, Chang S-F (2014) Discrete graph hashing. In: Advances in neural information processing systems, pp 3419\u20133427"},{"key":"2137_CR41","unstructured":"Wang D, Gao X, Wang X, He L (2015) Semantic topic multimodal hashing for cross-media retrieval. In: Twenty-Fourth International Joint Conference on Artificial Intelligence"},{"key":"2137_CR42","doi-asserted-by":"crossref","unstructured":"Zhang D, Li W-J (2014) Large-scale supervised multimodal hashing with semantic correlation maximization. In: Twenty-Eighth AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v28i1.8995"},{"key":"2137_CR43","doi-asserted-by":"crossref","unstructured":"Hotelling H (1992) Relations between two sets of variates. In: Breakthroughs in statistics. Springer, pp 162\u2013190","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"2137_CR44","doi-asserted-by":"publisher","first-page":"106188","DOI":"10.1016\/j.knosys.2020.106188","volume":"204","author":"H Qiang","year":"2020","unstructured":"Qiang H, Wan Y, Liu Z, Xiang L, Meng X (2020) Discriminative deep asymmetric supervised hashing for cross-modal retrieval. Knowl-Based Syst 204:106188","journal-title":"Knowl-Based Syst"},{"key":"2137_CR45","doi-asserted-by":"crossref","unstructured":"Liu X, Cheung Y-m, Hu Z, He Y, Zhong B (2020) Adversarial tri-fusion hashing network for imbalanced cross-modal retrieval. IEEE Transactions on Emerging Topics in Computational Intelligence","DOI":"10.1109\/TETCI.2020.3007143"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-02137-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-020-02137-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-02137-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T07:45:49Z","timestamp":1670831149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-020-02137-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,20]]},"references-count":45,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["2137"],"URL":"https:\/\/doi.org\/10.1007\/s10489-020-02137-w","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,20]]},"assertion":[{"value":"9 December 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"The authors declare that there is no conflict of interests regarding the publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of interests"}}]}}