{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:33:20Z","timestamp":1749184400544,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"39","license":[{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"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"],"DOI":"10.1007\/s11042-024-19581-2","type":"journal-article","created":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T07:02:01Z","timestamp":1718953321000},"page":"86537-86555","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep supervised fused similarity hashing for cross-modal retrieval"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0783-3585","authenticated-orcid":false,"given":"Wing W. Y.","family":"Ng","sequence":"first","affiliation":[]},{"given":"Yongzhi","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xing","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,21]]},"reference":[{"key":"19581_CR1","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-030-01246-5_13","volume-title":"Computer Vision - ECCV 2018","author":"Y Cao","year":"2018","unstructured":"Cao Y, Liu B, Long M, Wang J (2018) Cross-modal hamming hashing. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision - ECCV 2018. Springer International Publishing, Cham, pp 207\u2013223"},{"key":"19581_CR2","doi-asserted-by":"crossref","unstructured":"Cao Y, Long M, Wang J (2016) Correlation hashing network for efficient cross-modal retrieval. CoRR abs\/1602.06697. arXiv:1602.06697","DOI":"10.5244\/C.31.128"},{"key":"19581_CR3","doi-asserted-by":"publisher","unstructured":"Cao Z, Long M, Wang J, Yu PS (2017) Hashnet: deep learning to hash by continuation. In: 2017 IEEE International conference on computer vision (ICCV), pp 5609\u20135618. https:\/\/doi.org\/10.1109\/ICCV.2017.598","DOI":"10.1109\/ICCV.2017.598"},{"key":"19581_CR4","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of the British machine vision conference. BMVA Press","DOI":"10.5244\/C.28.6"},{"issue":"7","key":"19581_CR5","doi-asserted-by":"publisher","first-page":"2262","DOI":"10.1109\/TCSVT.2019.2911359","volume":"30","author":"ZD Chen","year":"2020","unstructured":"Chen ZD, Li CX, Luo X, Nie L, Zhang W, Xu XS (2020) Scratch: a scalable discrete matrix factorization hashing framework for cross-modal retrieval. IEEE Trans Circuits Syst Video Technol 30(7):2262\u20132275","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"19581_CR6","doi-asserted-by":"publisher","unstructured":"Cheng Q, Gu X (2021) Bridging multimedia heterogeneity gap via graph representation learning for cross-modal retrieval. Neural Netw 134:143\u2013162. https:\/\/doi.org\/10.1016\/j.neunet.2020.11.011. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0893608020304093","DOI":"10.1016\/j.neunet.2020.11.011"},{"key":"19581_CR7","doi-asserted-by":"publisher","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, CIVR09. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/1646396.1646452","DOI":"10.1145\/1646396.1646452"},{"issue":"8","key":"19581_CR8","doi-asserted-by":"publisher","first-page":"3893","DOI":"10.1109\/TIP.2018.2821921","volume":"27","author":"C Deng","year":"2018","unstructured":"Deng C, Chen Z, Liu X, Gao X, Tao D (2018) Triplet-based deep hashing network for cross-modal retrieval. IEEE Trans Image Process 27(8):3893\u20133903. https:\/\/doi.org\/10.1109\/TIP.2018.2821921","journal-title":"IEEE Trans Image Process"},{"key":"19581_CR9","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1016\/j.cviu.2009.03.008. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314209000575. Special issue on Image and Video Retrieval Evaluation","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"19581_CR10","doi-asserted-by":"publisher","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, ICMR \u201919, p 159167. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/3323873.3325045","DOI":"10.1145\/3323873.3325045"},{"issue":"4","key":"19581_CR11","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TMM.2018.2866771","volume":"21","author":"D Hu","year":"2019","unstructured":"Hu D, Nie F, Li X (2019) Deep binary reconstruction for cross-modal hashing. IEEE Trans Multimed 21(4):973\u2013985. https:\/\/doi.org\/10.1109\/TMM.2018.2866771","journal-title":"IEEE Trans Multimed"},{"key":"19581_CR12","doi-asserted-by":"publisher","unstructured":"Huang J, Min C, Jing L (2019) Unsupervised deep fusion cross-modal hashing. In: 2019 International conference on multimodal interaction, ICMI \u201919, p 358366. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/3340555.3353752","DOI":"10.1145\/3340555.3353752"},{"key":"19581_CR13","doi-asserted-by":"publisher","unstructured":"Huiskes MJ, Lew MS (2008) The mir flickr retrieval evaluation. In: Proceedings of the 1st ACM international conference on multimedia information retrieval, MIR08, p 3943. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/1460096.1460104","DOI":"10.1145\/1460096.1460104"},{"key":"19581_CR14","unstructured":"Ian J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Proceedings of the 27th international conference on neural information processing systems - vol 2, NIPS\u201914, p 26722680. MIT Press, Cambridge, MA, USA"},{"key":"19581_CR15","doi-asserted-by":"publisher","unstructured":"Jiang QY, Li WJ (2017) Deep cross-modal hashing. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 3270\u20133278. https:\/\/doi.org\/10.1109\/CVPR.2017.348","DOI":"10.1109\/CVPR.2017.348"},{"issue":"6","key":"19581_CR16","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":"19581_CR17","doi-asserted-by":"publisher","unstructured":"Li C, Deng C, Li N, Liu W, Gao X, Tao D (2018) Self-supervised adversarial hashing networks for cross-modal retrieval. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 4242\u20134251. https:\/\/doi.org\/10.1109\/CVPR.2018.00446","DOI":"10.1109\/CVPR.2018.00446"},{"key":"19581_CR18","doi-asserted-by":"publisher","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, MULTIMEDIA \u201903, p 604611. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/957013.957143","DOI":"10.1145\/957013.957143"},{"key":"19581_CR19","doi-asserted-by":"publisher","unstructured":"Liu H, Ji R, Wu Y, Huang F, Zhang B (2017) Cross-modality binary code learning via fusion similarity hashing. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 6345\u20136353. https:\/\/doi.org\/10.1109\/CVPR.2017.672","DOI":"10.1109\/CVPR.2017.672"},{"issue":"2","key":"19581_CR20","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1109\/TBDATA.2019.2954516","volume":"8","author":"X Liu","year":"2022","unstructured":"Liu X, Yu G, Domeniconi C, Wang J, Xiao G, Guo M (2022) Weakly supervised cross-modal hashing. IEEE Trans on Big Data 8(2):552\u2013563. https:\/\/doi.org\/10.1109\/TBDATA.2019.2954516","journal-title":"IEEE Trans on Big Data"},{"key":"19581_CR21","first-page":"1","volume":"60","author":"Y Liu","year":"2021","unstructured":"Liu Y, Li Q, Yuan Y, Du Q, Wang Q (2021) Abnet: adaptive balanced network for multiscale object detection in remote sensing imagery. IEEE Trans Geosci Remote Sens 60:1\u201314","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"19581_CR22","doi-asserted-by":"publisher","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, SIGIR \u201916, p 579588. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/2911451.2911493","DOI":"10.1145\/2911451.2911493"},{"key":"19581_CR23","doi-asserted-by":"publisher","unstructured":"Mandal D, Chaudhury KN, Biswas S (2017) Generalized semantic preserving hashing for n-label cross-modal retrieval. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 2633\u20132641. https:\/\/doi.org\/10.1109\/CVPR.2017.282","DOI":"10.1109\/CVPR.2017.282"},{"issue":"9","key":"19581_CR24","doi-asserted-by":"publisher","first-page":"2345","DOI":"10.1109\/TMM.2019.2954741","volume":"22","author":"D Mandal","year":"2020","unstructured":"Mandal D, Rao P, Biswas S (2020) Semi-supervised cross-modal retrieval with label prediction. IEEE Trans Multimed 22(9):2345\u20132353. https:\/\/doi.org\/10.1109\/TMM.2019.2954741","journal-title":"IEEE Trans Multimed"},{"key":"19581_CR25","doi-asserted-by":"publisher","unstructured":"Mao G, Yuan Y, Xiaoqiang L (2018) Deep cross-modal retrieval for remote sensing image and audio. In: 2018 10th IAPR workshop on pattern recognition in remote sensing (PRRS), pp 1\u20137. https:\/\/doi.org\/10.1109\/PRRS.2018.8486338","DOI":"10.1109\/PRRS.2018.8486338"},{"issue":"9","key":"19581_CR26","doi-asserted-by":"publisher","first-page":"3669","DOI":"10.1109\/TCSVT.2020.3042972","volume":"31","author":"X Nie","year":"2021","unstructured":"Nie X, Liu X, Xi X, Li C, Yin Y (2021) Fast unmediated hashing for cross-modal retrieval. IEEE Trans Circuits Syst Video Technol 31(9):3669\u20133678. https:\/\/doi.org\/10.1109\/TCSVT.2020.3042972","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"1","key":"19581_CR27","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1109\/TCSVT.2020.2974877","volume":"31","author":"X Nie","year":"2021","unstructured":"Nie X, Wang B, Li J, Hao F, Jian M, Yin Y (2021) Deep multiscale fusion hashing for cross-modal retrieval. IEEE Trans Circuits Syst Video Technol 31(1):401\u2013410","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"9","key":"19581_CR28","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. https:\/\/doi.org\/10.1109\/TCSVT.2017.2705068","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"12","key":"19581_CR29","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"A Smeulders","year":"2000","unstructured":"Smeulders A, Worring M, Santini S, Gupta A, Jain R (2000) Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 22(12):1349\u20131380. https:\/\/doi.org\/10.1109\/34.895972","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"19581_CR30","unstructured":"Srivastava N, Salakhutdinov RR (2012) Multimodal learning with deep boltzmann machines. Adv In Neural Inform Process Syst 25: 22222230"},{"key":"19581_CR31","doi-asserted-by":"publisher","unstructured":"Su S, Zhong Z, Zhang C (2019) Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval. In: 2019 IEEE\/CVF International conference on computer vision (ICCV), pp 3027\u20133035. https:\/\/doi.org\/10.1109\/ICCV.2019.00312","DOI":"10.1109\/ICCV.2019.00312"},{"issue":"10","key":"19581_CR32","doi-asserted-by":"publisher","first-page":"2703","DOI":"10.1109\/TCSVT.2017.2723302","volume":"28","author":"D Wang","year":"2018","unstructured":"Wang D, Wang Q, Gao X (2018) Robust and flexible discrete hashing for cross-modal similarity search. IEEE Trans Circuits Syst Video Technol 28(10):2703\u20132715. https:\/\/doi.org\/10.1109\/TCSVT.2017.2723302","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"19581_CR33","unstructured":"Wang J, Shen HT, Song J, Ji J (2014) Hashing for similarity search: a survey"},{"key":"19581_CR34","first-page":"1","volume":"60","author":"Q Wang","year":"2022","unstructured":"Wang Q, Liu Y, Xiong Z, Yuan Y (2022) Hybrid feature aligned network for salient object detection in optical remote sensing imagery. IEEE Trans Geosci Remote Sens 60:1\u201315","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"19581_CR35","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: Proceedings of the 27th international joint conference on artificial intelligence, IJCAI\u201918, p 28542860. AAAI Press","DOI":"10.24963\/ijcai.2018\/396"},{"key":"19581_CR36","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. https:\/\/aaai.org\/ocs\/index.php\/AAAI\/AAAI17\/paper\/view\/14326","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"19581_CR37","doi-asserted-by":"crossref","unstructured":"Yu E, Ma J, Sun J, Chang X, Zhang H, Hauptmann AG (2021) Deep discrete cross-modal hashing with multiple supervision. Neurocomputing","DOI":"10.1016\/j.neucom.2021.11.035"},{"issue":"5","key":"19581_CR38","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TMM.2018.2877127","volume":"21","author":"E Yu","year":"2019","unstructured":"Yu E, Sun J, Li J, Chang X, Han XH, Hauptmann AG (2019) Adaptive semi-supervised feature selection for cross-modal retrieval. IEEE Trans Multimedia 21(5):1276\u20131288. https:\/\/doi.org\/10.1109\/TMM.2018.2877127","journal-title":"IEEE Trans Multimedia"},{"key":"19581_CR39","doi-asserted-by":"publisher","unstructured":"Yu Z, Wu F, Yang Y, Tian Q, Luo J, Zhuang Y (2014) Discriminative coupled dictionary hashing for fast cross-media retrieval. SIGIR 14, p 395404. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/2600428.2609563. https:\/\/doi.org\/10.1145\/2600428.2609563","DOI":"10.1145\/2600428.2609563"},{"key":"19581_CR40","doi-asserted-by":"publisher","unstructured":"Zeng D, Yu Y, Oyama K (2020) Deep triplet neural networks with cluster-cca for audio-visual cross-modal retrieval. ACM Trans Multimedia Comput Commun Appl 16(3). https:\/\/doi.org\/10.1145\/3387164. https:\/\/doi.org\/10.1145\/3387164","DOI":"10.1145\/3387164"},{"key":"19581_CR41","doi-asserted-by":"publisher","unstructured":"Zhang D, Wu J (2020) Scalable discrete matrix factorization and semantic autoencoder for cross-media retrieval. IEEE Trans Cybern pp 1\u201314 X. https:\/\/doi.org\/10.1109\/TCYB.2020.3032017","DOI":"10.1109\/TCYB.2020.3032017"},{"key":"19581_CR42","doi-asserted-by":"crossref","unstructured":"Zhang J, Peng Y, Yuan M (2018) Unsupervised generative adversarial cross-modal hashing. In: Thirty-second aaai conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11263"},{"issue":"2","key":"19581_CR43","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. https:\/\/doi.org\/10.1109\/TCYB.2018.2868826","journal-title":"IEEE Trans Cybern"},{"key":"19581_CR44","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1016\/j.image.2020.116131. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0923596520302344","DOI":"10.1016\/j.image.2020.116131"},{"key":"19581_CR45","doi-asserted-by":"publisher","unstructured":"Zou X, Wu S, Zhang N, Bakker EM (2022) Multi-label modality enhanced attention based self-supervised deep cross-modal hashing. Knowledge-Based Systems 239, 107927. https:\/\/doi.org\/10.1016\/j.knosys.2021.107927. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S095070512101073X","DOI":"10.1016\/j.knosys.2021.107927"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19581-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19581-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19581-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T13:16:56Z","timestamp":1732022216000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19581-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,21]]},"references-count":45,"journal-issue":{"issue":"39","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["19581"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19581-2","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,6,21]]},"assertion":[{"value":"1 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 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":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}