{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:47:49Z","timestamp":1767991669387,"version":"3.49.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"39","license":[{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Department of Science and Technology","award":["IFA17-221"],"award-info":[{"award-number":["IFA17-221"]}]},{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"crossref","award":["CRG\/2022\/007807"],"award-info":[{"award-number":["CRG\/2022\/007807"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-025-21067-8","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T08:01:20Z","timestamp":1753948880000},"page":"47817-47854","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-view multi-label canonical correlation analysis for cross-modal multimedia retrieval"],"prefix":"10.1007","volume":"84","author":[{"given":"Asha","family":"Rani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rushil","family":"Sanghavi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2317-2641","authenticated-orcid":false,"given":"Yashaswi","family":"Verma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,31]]},"reference":[{"issue":"3\u20134","key":"21067_CR1","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1093\/biomet\/28.3-4.321","volume":"28","author":"H Hotelling","year":"1936","unstructured":"Hotelling H (1936) Relations Between Two Sets of Variates. Biometrika 28(3\u20134):321\u2013377","journal-title":"Biometrika"},{"issue":"12","key":"21067_CR2","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon DR, Szedmak S, Shawe-Taylor J (2004) Canonical correlation analysis: An overview with application to learning methods. Neural Comput 16(12):2639\u20132664","journal-title":"Neural Comput"},{"key":"21067_CR3","doi-asserted-by":"crossref","unstructured":"Ranjan V, Rasiwasia N, Jawahar CV (2015) Multi-label cross-modal retrieval. In: ICCV","DOI":"10.1109\/ICCV.2015.466"},{"key":"21067_CR4","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Burges CJC, Bottou L, Welling M, Ghahramani Z, Weinberger KQ (eds) Adv Neural Inform Process Syst pp 3111\u20133119"},{"issue":"4","key":"21067_CR5","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, Hernandez CA, Gonzalez JA, Lopez-Lopez A, Montes MM, Morales EF, Sucar LE, Pineda LV, 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":"21067_CR6","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00c3\u00a1r P, Zitnick C (2014) Microsoft coco: Common objects in context. In: ECCV","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"21067_CR7","doi-asserted-by":"crossref","unstructured":"Huiskes MJ, Lew MS (2008) The MIR Flickr retrieval evaluation. In: ACM International conference on multimedia information retrieval. ACM, New York, NY, USA","DOI":"10.1145\/1460096.1460104"},{"key":"21067_CR8","doi-asserted-by":"crossref","unstructured":"Sanghavi R, Verma Y (2022) Multi-view multi-label canonical correlation analysis for cross-modal matching and retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) workshops, pp 4701\u20134710","DOI":"10.1109\/CVPRW56347.2022.00516"},{"key":"21067_CR9","first-page":"1247","volume":"28","author":"G Andrew","year":"2013","unstructured":"Andrew G, Arora R, Bilmes JA, Livescu K (2013) Deep canonical correlation analysis. In: ICML 28:1247\u20131255","journal-title":"Deep canonical correlation analysis. In: ICML"},{"key":"21067_CR10","unstructured":"Wang W, Arora R, Livescu K, Bilmes JA (2015) On deep multi-view representation learning. In: ICML, pp 1083\u20131092"},{"key":"21067_CR11","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.neucom.2018.11.042","volume":"331","author":"Y Wu","year":"2019","unstructured":"Wu Y, Wang S, Huang Q (2019) Multi-modal semantic autoencoder for cross-modal retrieval. Neurocomputing 331:165\u2013175","journal-title":"Neurocomputing"},{"key":"21067_CR12","doi-asserted-by":"crossref","unstructured":"Zhan Y-W, Wang Y, Sun Y, Wu X-M, Luo X, Xu X-S (2022) Discrete online cross-modal hashing. Pattern Recogn 122:108262","DOI":"10.1016\/j.patcog.2021.108262"},{"key":"21067_CR13","doi-asserted-by":"crossref","unstructured":"Qian S, Xue D, Fang Q, Xu C (2023) Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrieval. IEEE Trans Pattern Anal Mach Intell 45(4)","DOI":"10.1109\/TPAMI.2022.3188547"},{"issue":"2","key":"21067_CR14","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/s11263-013-0658-4","volume":"106","author":"Y Gong","year":"2013","unstructured":"Gong Y, Ke Q, Isard M, Lazebnik S (2013) A multi-view embedding space for modeling internet images, tags, and their semantics. IJCV 106(2):210\u2013233","journal-title":"IJCV"},{"key":"21067_CR15","doi-asserted-by":"crossref","unstructured":"Rasiwasia N, Pereira JC, Coviello E, Doyle G, Lanckriet GRG, Levy R, Vasconcelos N (2010) A new approach to cross-modal multimedia retrieval. In: ACM MM","DOI":"10.1145\/1873951.1873987"},{"key":"21067_CR16","doi-asserted-by":"crossref","unstructured":"Malinowski M, Rohrbach M, Fritz M (2015) Ask your neurons: A neural-based approach to answering questions about images. In: ICCV","DOI":"10.1109\/ICCV.2015.9"},{"key":"21067_CR17","doi-asserted-by":"crossref","unstructured":"Hao W-L, Zhang Z, Guan H (2018) CMCGAN: A uniform framework for cross-modal visual-audio mutual generation. In: AAAI, pp 6886\u20136893","DOI":"10.1609\/aaai.v32i1.12329"},{"key":"21067_CR18","doi-asserted-by":"crossref","unstructured":"Zou WY, Socher R, Cer DM, Manning CD (2013) Bilingual word embeddings for phrase-based machine translation. In: EMNLP, pp 1393\u20131398","DOI":"10.18653\/v1\/D13-1141"},{"key":"21067_CR19","unstructured":"Rasiwasia N, Mahajan D, Mahadevan V, Aggarwal G (2014) Cluster canonical correlation analysis. In: AISTATS"},{"key":"21067_CR20","doi-asserted-by":"crossref","unstructured":"Sharma A, Kumar A, III HD, Jacobs DW (2012) Generalized multiview analysis: A discriminative latent space. In: CVPR","DOI":"10.1109\/CVPR.2012.6247923"},{"issue":"2s","key":"21067_CR21","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/3314577","volume":"15","author":"S Wang","year":"2019","unstructured":"Wang S, Guo D, Xu X, Zhuo L, Wang M (2019) Cross-modality retrieval by joint correlation learning. ACM Trans Multim Comput Commun Appl 15(2s):56\u201315616","journal-title":"ACM Trans Multim Comput Commun Appl"},{"key":"21067_CR22","doi-asserted-by":"crossref","unstructured":"Shu X, Zhao G (2021) Scalable multi-label canonical correlation analysis for cross-modal retrieval. Pattern Recognit 115:107905","DOI":"10.1016\/j.patcog.2021.107905"},{"key":"21067_CR23","doi-asserted-by":"crossref","unstructured":"Chen W, Liu Y, Bakker EM, Lew MS (2021) Integrating information theory and adversarial learning for cross-modal retrieval. Pattern Recogn 117:107983","DOI":"10.1016\/j.patcog.2021.107983"},{"key":"21067_CR24","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: Data, models and evaluation metrics. J Artif Intell Res 47:853\u2013899","journal-title":"J Artif Intell Res"},{"key":"21067_CR25","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.cviu.2016.10.001","volume":"154","author":"Y Verma","year":"2017","unstructured":"Verma Y, Jawahar CV (2017) A support vector approach for cross-modal search of images and texts. Comput Vis Image Underst 154:48\u201363","journal-title":"Comput Vis Image Underst"},{"key":"21067_CR26","unstructured":"Frome A, Corrado GS, Shlens J, Bengio S, Dean J, Ranzato MA, Mikolov T (2013) DeViSE: A deep visual-semantic embedding model. In: Advances in neural information processing systems"},{"key":"21067_CR27","doi-asserted-by":"crossref","unstructured":"Feng F, Wang X, Li R (2014) Cross-modal retrieval with correspondence autoencoder. In: ACM Multimedia, pp 7\u201316","DOI":"10.1145\/2647868.2654902"},{"key":"21067_CR28","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2015) Deep captioning with multimodal recurrent neural networks (m-rnn). In: ICLR"},{"key":"21067_CR29","doi-asserted-by":"crossref","unstructured":"Wang L, Li Y, Lazebnik S (2016) Learning deep structure-preserving image-text embeddings. In: IEEE Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.541"},{"key":"21067_CR30","unstructured":"Faghri F, Fleet DJ, Kiros J, Fidler S (2018) VSE++: Improving visual-semantic embeddings with hard negatives. In: BMVC"},{"key":"21067_CR31","doi-asserted-by":"crossref","unstructured":"Zhang Y, Lu H (2018) Deep cross-modal projection learning for image-text matching. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"21067_CR32","doi-asserted-by":"crossref","unstructured":"Sarafianos N, Xu X, Kakadiaris I (2019) Adversarial representation learning for text-to-image matching. In: IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00591"},{"key":"21067_CR33","doi-asserted-by":"crossref","unstructured":"Karpathy A, Li FF (2015) Deep visual-semantic alignments for generating image descriptions. In: IEEE Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"21067_CR34","doi-asserted-by":"crossref","unstructured":"Reed SE, Akata Z, Lee H, Schiele B (2016) Learning deep representations of fine-grained visual descriptions. In: CVPR","DOI":"10.1109\/CVPR.2016.13"},{"key":"21067_CR35","doi-asserted-by":"crossref","unstructured":"Wang X, Wang Y-F, Wang WY (2018) Watch, Listen, and Describe: Globally and locally aligned cross-modal attentions for video captioning. In: NAACL-HLT","DOI":"10.18653\/v1\/N18-2125"},{"key":"21067_CR36","doi-asserted-by":"crossref","unstructured":"Chen Y, Bazzani L (2020) Learning joint visual semantic matching embeddings for language-guided retrieval. In: ECCV","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"21067_CR37","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020"},{"key":"21067_CR38","unstructured":"Alayrac J, Recasens A, Schneider R, Arandjelovic R, Ramapuram J, Fauw JD, Smaira L, Dieleman S, Zisserman A (2020) Self-supervised multimodal versatile networks. In: NeurIPS 2020"},{"key":"21067_CR39","doi-asserted-by":"crossref","unstructured":"He J, Du J, Xu S, Ma W (2024) Preventing model collapse in deep canonical correlation analysis by noise regularization. In: Advances in neural information processing systems, vol 37, pp 82375\u201382410","DOI":"10.52202\/079017-2619"},{"key":"21067_CR40","doi-asserted-by":"crossref","unstructured":"Jin H, Zhang Y, Shi L, Zhang S, Kou F, Yang J, Zhu C, Luo J (2024) An end-to-end graph attention network hashing for cross-modal retrieval. In: Advances in Neural Information Processing Systems, vol 37, pp 2106\u20132126","DOI":"10.52202\/079017-0068"},{"key":"21067_CR41","unstructured":"Liu K, Gong Y, Cao Y, Ren Z, Peng D, Sun Y (2024) Dual semantic fusion hashing for multi-label cross-modal retrieval. In: Proceedings of the thirty-third international joint conference on artificial intelligence, pp 4569\u20134577"},{"key":"21067_CR42","doi-asserted-by":"crossref","unstructured":"Luo H, Zhang Z, Luo Y (2024) Exploiting descriptive completeness prior for cross modal hashing with incomplete labels. In: Advances in neural information processing systems, vol 37, pp 50826\u201350849","DOI":"10.52202\/079017-1608"},{"key":"21067_CR43","unstructured":"Li H, Hu P, Zhang Q, Peng X, Liu X, Yang M (2025) Test-time adaptation for cross-modal retrieval with query shift. In: The Thirteenth international conference on learning representations"},{"key":"21067_CR44","doi-asserted-by":"crossref","unstructured":"Lei Y, He F, Chen C, Mo Y, Li S, Xie D, Lu H (2024) MCAD: Multi-teacher cross-modal alignment distillation for efficient image-text retrieval. In: Findings of the association for computational linguistics: NAACL 2024, pp 1491\u20131503","DOI":"10.18653\/v1\/2024.findings-naacl.96"},{"key":"21067_CR45","doi-asserted-by":"crossref","unstructured":"Li Y, Wang W, Qu L, Nie L, Li W, Chua T-S (2024) Generative cross-modal retrieval: Memorizing images in multimodal language models for retrieval and beyond. In: Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long Papers), pp 11851\u201311861","DOI":"10.18653\/v1\/2024.acl-long.639"},{"key":"21067_CR46","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: EMNLP, vol 14, pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"21067_CR47","unstructured":"Wang J, Zucker JD (2000) Solving the multiple-instance problem: A lazy learning approach. In: ICML"},{"key":"21067_CR48","doi-asserted-by":"crossref","unstructured":"Guillaumin M, Mensink T, Verbeek JJ, Schmid C (2009) TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation. In: ICCV, pp 309\u2013316","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"21067_CR49","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR","DOI":"10.1109\/CVPR.2016.90"},{"key":"21067_CR50","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: A large-scale hierarchical image database. In: IEEE Conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21067_CR51","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. TACL 5:135\u2013146","journal-title":"TACL"},{"key":"21067_CR52","unstructured":"Weston J, Bengio S, Usunier N (2011) WSABIE: Scaling up to large vocabulary image annotation. In: IJCAI"},{"issue":"86","key":"21067_CR53","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(86):2579\u20132605","journal-title":"J Mach Learn Res"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-21067-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-025-21067-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-21067-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T07:25:43Z","timestamp":1765869943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-025-21067-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":53,"journal-issue":{"issue":"39","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["21067"],"URL":"https:\/\/doi.org\/10.1007\/s11042-025-21067-8","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"assertion":[{"value":"6 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work does not involve any human or animal subjects, hence no ethics approval\/consent is required.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}