{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:43:31Z","timestamp":1757313811424,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T00:00:00Z","timestamp":1660694400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T00:00:00Z","timestamp":1660694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s11042-022-13650-0","type":"journal-article","created":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T02:02:25Z","timestamp":1660701745000},"page":"7141-7157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cross-modal retrieval with dual optimization"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-8367","authenticated-orcid":false,"given":"Qingzhen","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,17]]},"reference":[{"key":"13650_CR1","unstructured":"Bellet A, Habrard A, Sebban M (2013) A survey on metric learning for feature vectors and structured data. CoRR, vol. abs\/1306.6709"},{"key":"13650_CR2","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1145\/2911996.2912000","volume-title":"Proceedings of the 2016 ACM on international conference on multimedia retrieval","author":"Y Cao","year":"2016","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"},{"key":"13650_CR3","volume-title":"Proceedings of the 8th ACM international conference on image and video retrieval","author":"T Chua","year":"2009","unstructured":"Chua T, 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 8th ACM international conference on image and video retrieval. ACM"},{"key":"13650_CR4","first-page":"7","volume-title":"Proceedings of the ACM international conference on multimedia","author":"F Feng","year":"2014","unstructured":"Feng F, Wang X, Li R (2014) Cross-modal retrieval with correspondence autoencoder. In: Proceedings of the ACM international conference on multimedia. ACM, pp 7\u201316"},{"issue":"12","key":"13650_CR5","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon DR, Szedm\u00e1k 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"},{"issue":"3","key":"13650_CR6","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TCYB.2018.2879846","volume":"50","author":"X Huang","year":"2020","unstructured":"Huang X, Peng Y, Yuan M (2020) MHTN: modal-adversarial hybrid transfer network for cross-modal retrieval. IEEE Trans Cybern 50(3):1047\u20131059","journal-title":"IEEE Trans Cybern"},{"key":"13650_CR7","first-page":"3270","volume-title":"2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017","author":"Q Jiang","year":"2017","unstructured":"Jiang Q, Li W (2017) Deep cross-modal hashing. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017. IEEE Computer Society, pp 3270\u20133278"},{"key":"13650_CR8","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1007\/978-3-642-33718-5_58","volume-title":"Computer vision - ECCV 2012 - 12th European conference on computer vision","author":"M Kan","year":"2012","unstructured":"Kan M, Shan S, Zhang H, Lao S, Chen X (2012) Multi-view discriminant analysis. In: Computer vision - ECCV 2012 - 12th European conference on computer vision, vol 7572. Springer, pp 808\u2013821"},{"issue":"1","key":"13650_CR9","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1109\/TPAMI.2015.2435740","volume":"38","author":"M Kan","year":"2016","unstructured":"Kan M, Shan S, Zhang H, Lao S, Chen X (2016) Multi-view discriminant analysis. IEEE Trans Pattern Anal Mach Intell 38(1):188\u2013194","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"13650_CR10","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/TMM.2015.2390499","volume":"17","author":"C Kang","year":"2015","unstructured":"Kang C, Xiang S, Liao S, Xu C, Pan C (2015) Learning consistent feature representation for cross-modal multimedia retrieval. IEEE Trans Multimedia 17(3):370\u2013381","journal-title":"IEEE Trans Multimedia"},{"issue":"2605","key":"13650_CR11","first-page":"2579","volume":"9","author":"VDM Laurens","year":"2008","unstructured":"Laurens VDM, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(2605):2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"13650_CR12","first-page":"604","volume-title":"Proceedings of the eleventh ACM international conference on multimedia, Berkeley, CA, USA, November 2-8, 2003","author":"D Li","year":"2003","unstructured":"Li D, Dimitrova N, Li M, Sethi IK (2003) Multimedia content processing through cross-modal association. In: Proceedings of the eleventh ACM international conference on multimedia, Berkeley, CA, USA, November 2-8, 2003. ACM, pp 604\u2013611"},{"issue":"6","key":"13650_CR13","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1109\/TMM.2016.2646180","volume":"19","author":"VE Liong","year":"2017","unstructured":"Liong VE, Lu J, Tan Y, Zhou J (2017) Deep coupled metric learning for cross-modal matching. IEEE Trans Multimedia 19(6):1234\u20131244","journal-title":"IEEE Trans Multimedia"},{"key":"13650_CR14","first-page":"3846","volume-title":"Proceedings of the twenty-fifth international joint conference on artificial intelligence","author":"Y Peng","year":"2016","unstructured":"Peng Y, Huang X, Qi J (2016) Cross-media shared representation by hierarchical learning with multiple deep networks. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence. IJCAI\/AAAI Press, pp 3846\u20133853"},{"issue":"2","key":"13650_CR15","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1109\/TMM.2017.2742704","volume":"20","author":"Y Peng","year":"2018","unstructured":"Peng Y, Qi J, Huang X, Yuan Y (2018) CCL: cross-modal correlation learning with multigrained fusion by hierarchical network. IEEE Trans Multimedia 20(2):405\u2013420","journal-title":"IEEE Trans Multimedia"},{"issue":"3","key":"13650_CR16","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1109\/TPAMI.2013.142","volume":"36","author":"JC Pereira","year":"2014","unstructured":"Pereira JC, Coviello E, Doyle G, Rasiwasia N, Lanckriet GRG, Levy R, Vasconcelos N (2014) 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":"13650_CR17","first-page":"4094","volume-title":"2015 IEEE international conference on computer vision","author":"V Ranjan","year":"2015","unstructured":"Ranjan V, Rasiwasia N, Jawahar CV (2015) Multi-label cross-modal retrieval. In: 2015 IEEE international conference on computer vision. IEEE Computer Society, pp 4094\u20134102"},{"key":"13650_CR18","first-page":"139","volume-title":"Proceedings of the 2010 workshop on creating speech and language data with Amazon\u2019s mechanical Turk","author":"C Rashtchian","year":"2010","unstructured":"Rashtchian C, Young P, Hodosh M, Hockenmaier J (2010) Collecting image annotations using amazon\u2019s mechanical turk. In: Proceedings of the 2010 workshop on creating speech and language data with Amazon\u2019s mechanical Turk. Association for Computational Linguistics, pp 139\u2013147"},{"key":"13650_CR19","first-page":"1849","volume-title":"Advances in neural information processing systems 29: annual conference on neural information processing systems 2016","author":"K Sohn","year":"2016","unstructured":"Sohn K (2016) Improved deep metric learning with multi-class n-pair loss objective. In: Advances in neural information processing systems 29: annual conference on neural information processing systems 2016, pp 1849\u20131857"},{"key":"13650_CR20","doi-asserted-by":"crossref","first-page":"4004","DOI":"10.1109\/CVPR.2016.434","volume-title":"2016 IEEE conference on computer vision and pattern recognition","author":"HO Song","year":"2016","unstructured":"Song HO, Xiang Y, Jegelka S, Savarese S (2016) Deep metric learning via lifted structured feature embedding. In: 2016 IEEE conference on computer vision and pattern recognition. IEEE Computer Society, pp 4004\u20134012"},{"key":"13650_CR21","doi-asserted-by":"publisher","first-page":"121812","DOI":"10.1016\/j.physa.2019.121812","volume":"532","author":"C Sun","year":"2019","unstructured":"Sun C, Wang C, Lai W (2019) Gait analysis and recognition prediction of the human skeleton based on migration learning. Phys A: Stat Mech Appl 532:121812","journal-title":"Phys A: Stat Mech Appl"},{"issue":"3","key":"13650_CR22","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1049\/iet-ipr.2018.5277","volume":"13","author":"S Unar","year":"2019","unstructured":"Unar S, Wang X, Zhang C, Wang C (2019) Detected text-based image retrieval approach for textual images. IET Image Process 13(3):515\u2013521","journal-title":"IET Image Process"},{"issue":"7","key":"13650_CR23","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1049\/iet-ipr.2019.0098","volume":"13","author":"S Unar","year":"2019","unstructured":"Unar S, Wang X, Wang C, Wang M (2019) New strategy for CBIR by combining low-level visual features with a colour descriptor. IET Image Process 13(7):1191\u20131200","journal-title":"IET Image Process"},{"key":"13650_CR24","doi-asserted-by":"crossref","unstructured":"Wang C, Lai W (2021) A fuzzy model of wearable network real-time health monitoring system on pharmaceutical industry. Pers Ubiquit Comput 25:485\u2013493","DOI":"10.1007\/s00779-019-01247-8"},{"key":"13650_CR25","volume-title":"4th international conference on learning representations","author":"W Wang","year":"2016","unstructured":"Wang W, Livescu K (2016) Large-scale approximate kernel canonical correlation analysis. In: 4th international conference on learning representations"},{"issue":"1","key":"13650_CR26","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.jvcir.2012.10.003","volume":"24","author":"X Wang","year":"2013","unstructured":"Wang X, Wang Z (2013) A novel method for image retrieval based on structure elements\u2019 descriptor. J Vis Commun Image Represent 24(1):63\u201374","journal-title":"J Vis Commun Image Represent"},{"issue":"10","key":"13650_CR27","doi-asserted-by":"publisher","first-page":"3293","DOI":"10.1016\/j.patcog.2014.04.020","volume":"47","author":"X Wang","year":"2014","unstructured":"Wang X, Wang Z (2014) The method for image retrieval based on multi-factors correlation utilizing block truncation coding. Pattern Recogn 47(10):3293\u20133303","journal-title":"Pattern Recogn"},{"key":"13650_CR28","first-page":"2088","volume-title":"IEEE international conference on computer vision","author":"K Wang","year":"2013","unstructured":"Wang K, He R, Wang W, Wang L, Tan T (2013) Learning coupled features paces for cross-modal matching. In: IEEE international conference on computer vision. IEEE Computer Society, pp 2088\u20132095"},{"key":"13650_CR29","unstructured":"Wang K, Yin Q, Wang W, Wu S, Wang L (2016) A comprehensive survey on cross-modal retrieval. CoRR, vol. abs\/1607.06215"},{"issue":"10","key":"13650_CR30","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1109\/TPAMI.2015.2505311","volume":"38","author":"K Wang","year":"2016","unstructured":"Wang K, He R, Wang L, Wang W, Tan T (2016) Joint feature selection and subspace learning for cross-modal retrieval. IEEE Trans Pattern Anal Mach Intell 38(10):2010\u20132023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"13650_CR31","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s00778-015-0391-4","volume":"25","author":"W Wang","year":"2016","unstructured":"Wang W, Yang X, Ooi BC, Zhang D, Zhuang Y (2016) Effective deep learning-based multi-modal retrieval. VLDB J 25(1):79\u2013101","journal-title":"VLDB J"},{"key":"13650_CR32","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1145\/3123266.3123326","volume-title":"Proceedings of the 2017 ACM on multimedia conference","author":"B Wang","year":"2017","unstructured":"Wang B, Yang Y, Xu X, Hanjalic A, Shen HT (2017) Adversarial cross-modal retrieval. In: Proceedings of the 2017 ACM on multimedia conference. ACM, pp 154\u2013162"},{"key":"13650_CR33","doi-asserted-by":"crossref","unstructured":"Wang C, Xu Q, Lin X, Liu S (2019) Research on data mining of permissions mode for android malware detection. Clust Comput 22(6):13337\u201313350","DOI":"10.1007\/s10586-018-1904-x"},{"key":"13650_CR34","first-page":"5207","volume-title":"IEEE conference on computer vision and pattern recognition","author":"X Wang","year":"2019","unstructured":"Wang X, Hua Y, Kodirov E, Hu G, Garnier R, Robertson NM (2019) Ranked list loss for deep metric learning. In: IEEE conference on computer vision and pattern recognition. Computer Vision Foundation \/ IEEE, pp 5207\u20135216"},{"issue":"12","key":"13650_CR35","doi-asserted-by":"publisher","first-page":"4440","DOI":"10.1109\/TCSVT.2019.2960507","volume":"30","author":"C Wang","year":"2020","unstructured":"Wang C, Wang X, Xia Z, Ma B, Shi Y (2020) Image description with polar harmonic fourier moments. IEEE Trans Circuits Syst Video Technol 30(12):4440\u20134452","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"13650_CR36","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1145\/2623330.2623688","volume-title":"The 20th ACM SIGKDD international conference on knowledge discovery and data mining","author":"Y Wei","year":"2014","unstructured":"Wei Y, Song Y, Zhen Y, Liu B, Yang Q (2014) Scalable heterogeneous translated hashing. In: The 20th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 791\u2013800"},{"issue":"2","key":"13650_CR37","first-page":"449","volume":"47","author":"Y Wei","year":"2017","unstructured":"Wei Y, Zhao Y, Lu C, Wei S, Liu L, Zhu Z, Yan S (2017) Cross-modal retrieval with CNN visual features: a new baseline. IEEE Trans Cybern 47(2):449\u2013460","journal-title":"IEEE Trans Cybern"},{"key":"13650_CR38","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1145\/2502081.2502097","volume-title":"ACM Multimedia Conference","author":"F Wu","year":"2013","unstructured":"Wu F, Lu X, Zhang Z, Yan S, Rui Y, Zhuang Y (2013) Cross-media semantic representation via bi-directional learning to rank. In: ACM Multimedia Conference. ACM, pp 877\u2013886"},{"key":"13650_CR39","first-page":"3441","volume-title":"IEEE conference on computer vision and pattern recognition","author":"F Yan","year":"2015","unstructured":"Yan F, Mikolajczyk K (2015) Deep correlation for matching images and text. In: IEEE conference on computer vision and pattern recognition. IEEE Computer Society, pp 3441\u20133450"},{"issue":"1","key":"13650_CR40","doi-asserted-by":"publisher","first-page":"9:1","DOI":"10.1145\/3374754","volume":"16","author":"Z Yang","year":"2020","unstructured":"Yang Z, Lin Z, Kang P, Lv J, Li Q, Liu W (2020) Learning shared semantic space with correlation alignment for cross-modal event retrieval. ACM Trans Multimed Comput Commun Appl 16(1):9:1\u20139:22","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"13650_CR41","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/TIFS.2019.2921454","volume":"15","author":"M Ye","year":"2020","unstructured":"Ye M, Lan X, Wang Z, Yuen PC (2020) Bi-directional center-constrained top-ranking for visible thermal person re-identification. IEEE Trans Inf Forensics Secur 15:407\u2013419","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"13650_CR42","first-page":"814","volume-title":"IEEE international conference on computer vision","author":"Y Yuan","year":"2017","unstructured":"Yuan Y, Yang K, Zhang C (2017) Hard-aware deeply cascaded embedding. In: IEEE international conference on computer vision. IEEE Computer Society, pp 814\u2013823"},{"issue":"6","key":"13650_CR43","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1109\/TCSVT.2013.2276704","volume":"24","author":"X Zhai","year":"2014","unstructured":"Zhai X, Peng Y, Xiao J (2014) Learning cross-media joint representation with sparse and semisupervised regularization. IEEE Trans Circuits Syst Video Technol 24(6):965\u2013978","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"13650_CR44","first-page":"1355","volume-title":"Proceedings of the 2016 ACM conference on multimedia conference","author":"L Zhang","year":"2016","unstructured":"Zhang L, Ma B, Li G, Huang Q, Tian Q (2016) Pl-ranking: a novel ranking method for cross-modal retrieval. In: Proceedings of the 2016 ACM conference on multimedia conference. ACM, pp 1355\u20131364"},{"issue":"2","key":"13650_CR45","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1109\/TCYB.2018.2868826","volume":"50","author":"J Zhang","year":"2020","unstructured":"Zhang J, Peng Y, Yuan M (2020) SCH-GAN: semi-supervised cross-modal hashing by generative adversarial network. IEEE Trans Cybern. 50(2):489\u2013502","journal-title":"IEEE Trans Cybern."},{"key":"13650_CR46","first-page":"10394","volume-title":"IEEE conference on computer vision and pattern recognition","author":"L Zhen","year":"2019","unstructured":"Zhen L, Hu P, Wang X, Peng D (2019) Deep supervised cross-modal retrieval. In: IEEE conference on computer vision and pattern recognition, pp 10394\u201310403"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13650-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-13650-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13650-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T21:53:48Z","timestamp":1727819628000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-13650-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,17]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["13650"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-13650-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,8,17]]},"assertion":[{"value":"12 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2022","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 is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}