{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T13:31:52Z","timestamp":1763904712986},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Fundamental Research Funds for the Central Universities","award":["(SWU-KT22032)"],"award-info":[{"award-number":["(SWU-KT22032)"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s13735-023-00311-7","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T14:02:10Z","timestamp":1704722530000},"update-policy":"https:\/\/2.zoppoz.workers.dev:443\/http\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Text-assisted attention-based cross-modal hashing"],"prefix":"10.1007","volume":"13","author":[{"given":"Xiang","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihao","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwen","family":"Huo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkai","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,8]]},"reference":[{"issue":"9","key":"311_CR1","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TCSVT.2017.2705068","volume":"28","author":"Y Peng","year":"2018","unstructured":"Peng Y, Huang X, Zhao Y (2018) An overview of cross-media retrieval: concepts, methodologies, benchmarks, and challenges. IEEE Trans Circuits Syst Video Technol 28(9):2372\u20132385","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"311_CR2","unstructured":"Wang K, Yin Q, Wang W, Wu S, Wang L (2016) A comprehensive survey on cross-modal retrieval. arXiv preprint arXiv:1607.06215"},{"issue":"11","key":"311_CR3","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2016.2607421","volume":"25","author":"G Ding","year":"2016","unstructured":"Ding G, Guo Y, Zhou J, Gao Y (2016) Large-scale cross-modality search via collective matrix factorization hashing. IEEE Trans Image Process 25(11):5427\u20135440","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"311_CR4","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1109\/TMM.2016.2625747","volume":"19","author":"K Ding","year":"2016","unstructured":"Ding K, Fan B, Huo C, Xiang S, Pan C (2016) Cross-modal hashing via rank-order preserving. IEEE Trans Multimed 19(3):571\u2013585","journal-title":"IEEE Trans Multimed"},{"key":"311_CR5","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":"311_CR6","unstructured":"Kumar S, Udupa R (2011) Learning hash functions for cross-view similarity search. In: Twenty-second international joint conference on artificial intelligence"},{"key":"311_CR7","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":"311_CR8","doi-asserted-by":"crossref","unstructured":"Zhou J, Ding G, Guo Y (2014) Latent semantic sparse hashing for cross-modal similarity search. In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval, pp 415\u2013424","DOI":"10.1145\/2600428.2609610"},{"key":"311_CR9","doi-asserted-by":"crossref","unstructured":"Bronstein MM, Bronstein AM, 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":"311_CR10","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":"311_CR11","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"},{"issue":"2","key":"311_CR12","first-page":"427","volume":"16","author":"W Fei","year":"2013","unstructured":"Fei W, Zhou Yu, Yang Y, Tang S, Zhang Y, Zhuang Y (2013) Sparse multi-modal hashing. IEEE Trans Multimed 16(2):427\u2013439","journal-title":"IEEE Trans Multimed"},{"key":"311_CR13","doi-asserted-by":"crossref","unstructured":"Zhang D, Li WJ (2014) Large-scale supervised multimodal hashing with semantic correlation maximization. In: Proceedings of the AAAI conference on artificial intelligence, vol 28","DOI":"10.1609\/aaai.v28i1.8995"},{"issue":"8","key":"311_CR14","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798\u20131828","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"311_CR15","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"key":"311_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"311_CR17","doi-asserted-by":"crossref","unstructured":"Cao Y, Long M, Wang J, Yang Q, Yu PS (2016) Deep visual-semantic hashing for cross-modal retrieval. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1445\u20131454","DOI":"10.1145\/2939672.2939812"},{"key":"311_CR18","doi-asserted-by":"crossref","unstructured":"Jiang QY, Li WJ (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":"311_CR19","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick C (2014) Microsoft coco: Common objects in context. In: Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, 6\u201312 Sept, 2014, Proceedings, Part V 13. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"311_CR20","doi-asserted-by":"crossref","unstructured":"Shen Y, Liu L, Shao L, Song J (2017) Deep binaries: encoding semantic-rich cues for efficient textual-visual cross retrieval. In: Proceedings of the IEEE international conference on computer vision, pp 4097\u20134106","DOI":"10.1109\/ICCV.2017.441"},{"key":"311_CR21","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: Proceedings of the AAAI conference on artificial intelligence, vol 31","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"311_CR22","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"},{"issue":"12","key":"311_CR23","doi-asserted-by":"publisher","first-page":"3101","DOI":"10.1109\/TMM.2020.2969792","volume":"22","author":"X Ma","year":"2020","unstructured":"Ma X, Zhang T, Changsheng X (2020) Multi-level correlation adversarial hashing for cross-modal retrieval. IEEE Trans Multimed 22(12):3101\u20133114","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"311_CR24","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TPAMI.2017.2699960","volume":"40","author":"J Wang","year":"2017","unstructured":"Wang J, Zhang T, Sebe N, Shen HT (2017) A survey on learning to hash. IEEE Trans Pattern Anal Mach intel 40(4):769\u2013790","journal-title":"IEEE Trans Pattern Anal Mach intel"},{"key":"311_CR25","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.neucom.2020.03.019","volume":"400","author":"X Wang","year":"2020","unstructured":"Wang X, Zou X, Bakker EM, Song W (2020) Self-constraining and attention-based hashing network for bit-scalable cross-modal retrieval. Neurocomputing 400:255\u2013271","journal-title":"Neurocomputing"},{"key":"311_CR26","doi-asserted-by":"publisher","first-page":"107927","DOI":"10.1016\/j.knosys.2021.107927","volume":"239","author":"X Zou","year":"2022","unstructured":"Zou X, Wu S, Zhang N, Bakker EM (2022) Multi-label modality enhanced attention based self-supervised deep cross-modal hashing. Knowl Based Syst 239:107927","journal-title":"Knowl Based Syst"},{"key":"311_CR27","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst"},{"key":"311_CR28","doi-asserted-by":"crossref","unstructured":"Yang Z, Yang D, Dyer C, He X, Smola A, Hovy E (2016) Hierarchical attention networks for document classification. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 1480\u20131489","DOI":"10.18653\/v1\/N16-1174"},{"key":"311_CR29","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":"311_CR30","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: International conference on machine learning"},{"key":"311_CR31","doi-asserted-by":"crossref","unstructured":"Cao Y, Long M, Wang J, Yu PS (2016) Correlation hashing network for efficient cross-modal retrieval. arXiv preprint arXiv:1602.06697","DOI":"10.5244\/C.31.128"},{"key":"311_CR32","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":"311_CR33","doi-asserted-by":"crossref","unstructured":"Chua TS, 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"},{"issue":"4","key":"311_CR34","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.cviu.2009.03.008","volume":"114","author":"HJ Escalante","year":"2010","unstructured":"Escalante HJ, Hern\u00e1ndez CA, Gonzalez JA, L\u00f3pez-L\u00f3pez A, Montes M, Morales EF, Enrique Sucar L, Villasenor L, Grubinger M (2010) The segmented and annotated IAPR TC-12 benchmark. Comput Vis Image Underst 114(4):419\u2013428","journal-title":"Comput Vis Image Underst"},{"key":"311_CR35","doi-asserted-by":"crossref","unstructured":"Mandal D, Chaudhury KN, Biswas S (2017) Generalized semantic preserving hashing for n-label cross-modal retrieval. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4076\u20134084","DOI":"10.1109\/CVPR.2017.282"},{"key":"311_CR36","doi-asserted-by":"crossref","unstructured":"Zou X, Wang X, Bakker EM, Wu S (2021) Multi-label semantics preserving based deep cross-modal hashing. Signal Process Image Commun 93:116131","DOI":"10.1016\/j.image.2020.116131"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00311-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/article\/10.1007\/s13735-023-00311-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00311-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T11:10:57Z","timestamp":1711624257000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/10.1007\/s13735-023-00311-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,8]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["311"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/s13735-023-00311-7","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,8]]},"assertion":[{"value":"19 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no declared competing interests of the authors that are pertinent to the subject matter of this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"3"}}