{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:45:50Z","timestamp":1786981550121,"version":"build-2736575974"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/s11042-024-20447-w","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T02:36:34Z","timestamp":1733106994000},"page":"2985-3014","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A novel approach for image retrieval in remote sensing using vision-language-based image caption generation"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2119-3479","authenticated-orcid":false,"given":"Prem Shanker","family":"Yadav","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh Kumar","family":"Tyagi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santosh Kumar","family":"Vipparthi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"20447_CR1","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1109\/JSTARS.2023.3236662","volume":"16","author":"W Zhou","year":"2023","unstructured":"Zhou W, Guan H, Li Z, Shao Z, Delavar MR (2023) Remote sensing image retrieval in the past decade: Achievements, challenges, and future directions. IEEE J Sel Top Appl Earth Observ Remote Sens 16:1447\u20131473","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"key":"20447_CR2","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.isprsjprs.2018.01.004","volume":"145","author":"W Zhou","year":"2018","unstructured":"Zhou W, Newsam S, Li C, Shao Z (2018) Patternnet: A benchmark dataset for performance evaluation of remote sensing image retrieval. ISPRS J Photogramm Remote Sens 145:197\u2013209","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"20447_CR3","doi-asserted-by":"publisher","first-page":"29561","DOI":"10.1007\/s11042-021-11045-1","volume":"80","author":"R Kapoor","year":"2021","unstructured":"Kapoor R, Sharma D, Gulati T (2021) State of the art content based image retrieval techniques using deep learning: a survey. Multimed Tools Appl 80:29561\u201329583","journal-title":"Multimed Tools Appl"},{"key":"20447_CR4","doi-asserted-by":"publisher","first-page":"4462","DOI":"10.1109\/JSTARS.2020.3013818","volume":"13","author":"G Hoxha","year":"2020","unstructured":"Hoxha G, Melgani F, Demir B (2020) Toward remote sensing image retrieval under a deep image captioning perspective. IEEE J Sel Top Appl Earth Observ Remote Sens 13:4462\u20134475","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"key":"20447_CR5","doi-asserted-by":"crossref","unstructured":"Dharani T, Aroquiaraj IL (2013) A survey on content based image retrieval, pp 485\u2013490. IEEE","DOI":"10.1109\/ICPRIME.2013.6496719"},{"key":"20447_CR6","doi-asserted-by":"crossref","unstructured":"Srivastava G, Srivastava R (2018) A survey on automatic image captioning, pp 74\u201383. Springer","DOI":"10.1007\/978-981-13-0023-3_8"},{"key":"20447_CR7","doi-asserted-by":"crossref","unstructured":"Wang C, Yang H, Bartz C, Meinel C (2016) Image captioning with deep bidirectional lstms, pp 988\u2013997","DOI":"10.1145\/2964284.2964299"},{"key":"20447_CR8","doi-asserted-by":"publisher","first-page":"24","DOI":"10.4236\/jcc.2022.104003","volume":"10","author":"NO Larsey","year":"2022","unstructured":"Larsey NO, Ahiaklo-Kuz RMK, Ncube J (2022) Content-based image retrieval with feature extraction and rotation invariance. J Comput Commun 10:24\u201331","journal-title":"J Comput Commun"},{"key":"20447_CR9","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.1109\/LGRS.2018.2847303","volume":"15","author":"F Ye","year":"2018","unstructured":"Ye F et al (2018) Remote sensing image retrieval using convolutional neural network features and weighted distance. IEEE Geosci Remote Sens Lett 15:1535\u20131539","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"20447_CR10","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1109\/LGRS.2019.2893772","volume":"16","author":"B Wang","year":"2019","unstructured":"Wang B, Lu X, Zheng X, Li X (2019) Semantic descriptions of high-resolution remote sensing images. IEEE Geosci Remote Sens Lett 16:1274\u20131278","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"20447_CR11","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.cviu.2019.04.004","volume":"184","author":"U Chaudhuri","year":"2019","unstructured":"Chaudhuri U, Banerjee B, Bhattacharya A (2019) Siamese graph convolutional network for content based remote sensing image retrieval. Comput Vis Image Understand 184:22\u201330","journal-title":"Comput Vis Image Understand"},{"key":"20447_CR12","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1109\/TGRS.2017.2756911","volume":"56","author":"Y Li","year":"2017","unstructured":"Li Y, Zhang Y, Huang X, Zhu H, Ma J (2017) Large-scale remote sensing image retrieval by deep hashing neural networks. IEEE Trans Geosci Remote Sens 56:950\u2013965","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"20447_CR13","doi-asserted-by":"publisher","first-page":"1927469","DOI":"10.1080\/23311916.2021.1927469","volume":"8","author":"IM Hameed","year":"2021","unstructured":"Hameed IM, Abdulhussain SH, Mahmmod BM (2021) Content-based image retrieval: A review of recent trends. Cogent Eng 8:1927469","journal-title":"Cogent Eng"},{"key":"20447_CR14","doi-asserted-by":"publisher","first-page":"120774","DOI":"10.1016\/j.eswa.2023.120774","volume":"232","author":"GS Vieira","year":"2023","unstructured":"Vieira GS, Fonseca AU, Sousa NM, Felix JP, Soares F (2023) A novel content-based image retrieval system with feature descriptor integration and accuracy noise reduction. Expert Syst Appl 232:120774","journal-title":"Expert Syst Appl"},{"key":"20447_CR15","doi-asserted-by":"publisher","first-page":"8931","DOI":"10.3390\/app10248931","volume":"10","author":"MMA Rahhal","year":"2020","unstructured":"Rahhal MMA, Bazi Y, Abdullah T, Mekhalfi ML, Zuair M (2020) Deep unsupervised embedding for remote sensing image retrieval using textual cues. Appl Sci 10:8931","journal-title":"Appl Sci"},{"key":"20447_CR16","doi-asserted-by":"publisher","first-page":"25697","DOI":"10.1007\/s11042-020-09251-4","volume":"79","author":"M Cornia","year":"2020","unstructured":"Cornia M, Baraldi L, Tavakoli HR, Cucchiara R (2020) A unified cycle-consistent neural model for text and image retrieval. Multimed Tools Appl 79:25697\u201325721","journal-title":"Multimed Tools Appl"},{"key":"20447_CR17","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.jvcir.2018.12.027","volume":"58","author":"N Xu","year":"2019","unstructured":"Xu N, Liu A-A, Liu J, Nie W, Su Y (2019) Scene graph captioner: Image captioning based on structural visual representation. J Vis Commun Image Represent 58:477\u2013485","journal-title":"J Vis Commun Image Represent"},{"key":"20447_CR18","doi-asserted-by":"crossref","unstructured":"Iyer S, Chaturvedi S, Dash T (2019) Image captioning-based image search engine: An alternative to retrieval by metadata, pp 181\u2013191. Springer","DOI":"10.1007\/978-981-13-1595-4_14"},{"key":"20447_CR19","doi-asserted-by":"publisher","first-page":"2942","DOI":"10.1109\/TMM.2019.2915033","volume":"21","author":"X Xiao","year":"2019","unstructured":"Xiao X, Wang L, Ding K, Xiang S, Pan C (2019) Deep hierarchical encoder-decoder network for image captioning. IEEE Trans Multimed 21:2942\u20132956","journal-title":"IEEE Trans Multimed"},{"key":"20447_CR20","first-page":"1","volume":"14","author":"C Wang","year":"2018","unstructured":"Wang C, Yang H, Meinel C (2018) Image captioning with deep bidirectional lstms and multi-task learning. ACM Trans Multimed Comput Commun Appl (TOMM) 14:1\u201320","journal-title":"ACM Trans Multimed Comput Commun Appl (TOMM)"},{"key":"20447_CR21","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1109\/TMM.2019.2941820","volume":"22","author":"N Xu","year":"2019","unstructured":"Xu N et al (2019) Multi-level policy and reward-based deep reinforcement learning framework for image captioning. IEEE Trans Multimed 22:1372\u20131383","journal-title":"IEEE Trans Multimed"},{"key":"20447_CR22","doi-asserted-by":"crossref","unstructured":"Zhao K, Xiong W (2024) Cooperative connection transformer for remote sensing image captioning. IEEE Trans Geosci Remote Sens","DOI":"10.1109\/TGRS.2024.3360089"},{"key":"20447_CR23","doi-asserted-by":"crossref","unstructured":"Song Z et\u00a0al (2024) Embedded heterogeneous attention transformer for cross-lingual image captioning. IEEE Trans Multimed","DOI":"10.1109\/TMM.2024.3384678"},{"key":"20447_CR24","doi-asserted-by":"publisher","first-page":"31787","DOI":"10.1007\/s11042-022-11997-y","volume":"81","author":"MN Vharkate","year":"2022","unstructured":"Vharkate MN, Musande VB (2022) Fusion based feature extraction and optimal feature selection in remote sensing image retrieval. Multimed Tools Appl 81:31787\u201331814","journal-title":"Multimed Tools Appl"},{"key":"20447_CR25","doi-asserted-by":"publisher","first-page":"15101","DOI":"10.1007\/s11042-018-6855-y","volume":"78","author":"L Yan","year":"2019","unstructured":"Yan L et al (2019) Deep linear discriminant analysis hashing for image retrieval. Multimed Tools Appl 78:15101\u201315119","journal-title":"Multimed Tools Appl"},{"key":"20447_CR26","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s40537-023-00693-9","volume":"10","author":"R Sasibhooshan","year":"2023","unstructured":"Sasibhooshan R, Kumaraswamy S, Sasidharan S (2023) Image caption generation using visual attention prediction and contextual spatial relation extraction. J Big Data 10:18","journal-title":"J Big Data"},{"key":"20447_CR27","doi-asserted-by":"crossref","unstructured":"Phueaksri I, Kastner MA, Kawanishi Y, Komamizu T, Ide I (2023) An approach to generate a caption for an image collection using scene graph generation. IEEE Access","DOI":"10.1109\/ACCESS.2023.3332098"},{"key":"20447_CR28","unstructured":"Shao Z, Han J, Marnerides D, Debattista K (2022) Region-object relation-aware dense captioning via transformer. IEEE Trans Neural Netw Learn Syst"},{"key":"20447_CR29","doi-asserted-by":"publisher","first-page":"8753","DOI":"10.1109\/TMM.2023.3241517","volume":"25","author":"Z Shao","year":"2023","unstructured":"Shao Z, Han J, Debattista K, Pang Y (2023) Textual context-aware dense captioning with diverse words. IEEE Trans Multimed 25:8753\u20138766","journal-title":"IEEE Trans Multimed"},{"key":"20447_CR30","doi-asserted-by":"crossref","unstructured":"Shao Z, Han J, Debattista K, Pang Y (2024) Dcmstrd: end-to-end dense captioning via multi-scale transformer decoding. IEEE Trans Multimed","DOI":"10.1109\/TMM.2024.3369863"},{"key":"20447_CR31","unstructured":"Goldberg DE (1989) Genetic algorithm in search, optimization and machine learning, addison. Wesley Publishing Company, Reading, MA 19"},{"key":"20447_CR32","doi-asserted-by":"crossref","unstructured":"Kennedy J, Eberhart R (1995) Particle swarm optimization. Proceedings of the IEEE international conference on neural networks, vol 4, pp 1942\u20131948","DOI":"10.1109\/ICNN.1995.488968"},{"key":"20447_CR33","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1162\/106454699568728","volume":"5","author":"M Dorigo","year":"1999","unstructured":"Dorigo M, Di Caro G, Gambardella LM (1999) Ant algorithms for discrete optimization. Artif Life 5:137\u2013172","journal-title":"Artif Life"},{"key":"20447_CR34","doi-asserted-by":"publisher","first-page":"105709","DOI":"10.1016\/j.knosys.2020.105709","volume":"195","author":"Q Askari","year":"2020","unstructured":"Askari Q, Younas I, Saeed M (2020) Political optimizer: A novel socio-inspired meta-heuristic for global optimization. Knowl-Based Syst 195:105709","journal-title":"Knowl-Based Syst"},{"key":"20447_CR35","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.matcom.2021.08.013","volume":"192","author":"FA Hashim","year":"2022","unstructured":"Hashim FA, Houssein EH, Hussain K, Mabrouk MS, Al-Atabany W (2022) Honey badger algorithm: New metaheuristic algorithm for solving optimization problems. Math Comput Simul 192:84\u2013110","journal-title":"Math Comput Simul"},{"key":"20447_CR36","doi-asserted-by":"crossref","unstructured":"Zhou L et al (2020) Unified vision-language pre-training for image captioning and vqa, vol 34, pp 13041\u201313049","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"20447_CR37","doi-asserted-by":"crossref","unstructured":"Liu Q, Wang J, Zhang D, Yang Y, Wang N (2018) Text features extraction based on tf-idf associating semantic, pp 2338\u20132343. IEEE","DOI":"10.1109\/CompComm.2018.8780663"},{"key":"20447_CR38","doi-asserted-by":"publisher","first-page":"021101","DOI":"10.1103\/PhysRevLett.98.021101","volume":"98","author":"DJ Kapner","year":"2007","unstructured":"Kapner DJ et al (2007) Tests of the gravitational inverse-square law below the dark-energy length scale. Phys Rev Lett 98:021101","journal-title":"Phys Rev Lett"},{"key":"20447_CR39","unstructured":"RSICD (Accessed on April 2022). https:\/\/github.com\/201528014227051\/RSICD_optimal"},{"key":"20447_CR40","unstructured":"Sydneycaptions (Accessed on April 2022). https:\/\/mega.nz\/folder\/pG4yTYYA#4c4buNFLibryZnlujsrwEQ"},{"key":"20447_CR41","unstructured":"UCM captions (Accessed on April 2022). https:\/\/mega.nz\/folder\/wCpSzSoS#RXzIlrv--TDt3ENZdKN8JA"},{"key":"20447_CR42","doi-asserted-by":"crossref","unstructured":"Chen C, Han J, Debattista K (2024) Virtual category learning: A semi-supervised learning method for dense prediction with extremely limited labels. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2024.3367416"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20447-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-20447-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20447-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T05:08:46Z","timestamp":1739336926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-20447-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["20447"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-20447-w","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"29 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"The research conducted for this manuscript did not require ethics approval as it did not involve human participants or animals.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}]}}