{"id":"https://openalex.org/W4293508747","doi":"https://doi.org/10.1109/lgrs.2022.3198234","title":"Exploring Transformer and Multilabel Classification for Remote Sensing Image Captioning","display_name":"Exploring Transformer and Multilabel Classification for Remote Sensing Image Captioning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4293508747","doi":"https://doi.org/10.1109/lgrs.2022.3198234"},"language":"en","primary_location":{"id":"doi:10.1109/lgrs.2022.3198234","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lgrs.2022.3198234","pdf_url":"https://ieeexplore.ieee.org/ielx7/8859/4357975/09855519.pdf","source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Geoscience and Remote Sensing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/8859/4357975/09855519.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056710972","display_name":"Hitesh Kandala","orcid":"https://orcid.org/0000-0002-6761-3368"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hitesh Kandala","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"raw_orcid":"https://orcid.org/0000-0002-6761-3368","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083424027","display_name":"Sudipan Saha","orcid":"https://orcid.org/0000-0002-9440-0720"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sudipan Saha","raw_affiliation_strings":["Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany","Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Ottobrunn, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9440-0720","affiliations":[{"raw_affiliation_string":"Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Ottobrunn, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020786167","display_name":"Biplab Banerjee","orcid":"https://orcid.org/0000-0001-8371-8138"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Biplab Banerjee","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"raw_orcid":"https://orcid.org/0000-0001-8371-8138","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068384981","display_name":"Xiao Xiang Zhu","orcid":"https://orcid.org/0000-0001-5530-3613"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiao Xiang Zhu","raw_affiliation_strings":["Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany","Remote Sensing Technology Institute, German Aerospace Center (DLR), We&#x00DF","ling, Germany","Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Ottobrunn, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5530-3613","affiliations":[{"raw_affiliation_string":"Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Remote Sensing Technology Institute, German Aerospace Center (DLR), We&#x00DF","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"ling, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of Aerospace and Geodesy, Chair of Data Science in Earth Observation, Technical University of Munich, Ottobrunn, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":{"value":1634,"currency":"EUR","value_usd":1762},"fwci":4.4046,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.95798255,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"19","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9751281142234802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8741734623908997},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6458518505096436},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6066104173660278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5533443093299866},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5133959054946899},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4452916085720062},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4438515901565552},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.43287375569343567},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3340204358100891},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32509106397628784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3228864073753357},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07520967721939087}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9751281142234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741734623908997},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6458518505096436},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6066104173660278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5533443093299866},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5133959054946899},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4452916085720062},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4438515901565552},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.43287375569343567},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3340204358100891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32509106397628784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3228864073753357},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07520967721939087},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lgrs.2022.3198234","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lgrs.2022.3198234","pdf_url":"https://ieeexplore.ieee.org/ielx7/8859/4357975/09855519.pdf","source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Geoscience and Remote Sensing Letters","raw_type":"journal-article"},{"id":"pmh:oai:elib.dlr.de:192680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/LGRS.2022.3198234>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Zeitschriftenbeitrag"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1772103","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1772103","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/lgrs.2022.3198234","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lgrs.2022.3198234","pdf_url":"https://ieeexplore.ieee.org/ielx7/8859/4357975/09855519.pdf","source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Geoscience and Remote Sensing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4132552849","display_name":null,"funder_award_id":"ERC- 2016-StG-714087","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G623313952","display_name":"K\u00fcnstliche Intelligenz in der Erdbeobachtung: Schlussfolgern, Unsicherheiten, Ethik und dar\u00fcber hinaus","funder_award_id":"01DD20001","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G7485680001","display_name":null,"funder_award_id":"ZT-I-PF-5-01","funder_id":"https://openalex.org/F4320325698","funder_display_name":"Helmholtz Association"},{"id":"https://openalex.org/G880257738","display_name":null,"funder_award_id":"W2-W3-100","funder_id":"https://openalex.org/F4320325698","funder_display_name":"Helmholtz Association"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320325698","display_name":"Helmholtz Association","ror":null},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293508747.pdf","grobid_xml":"https://content.openalex.org/works/W4293508747.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1980038761","https://openalex.org/W2097117768","https://openalex.org/W2183341477","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2766938848","https://openalex.org/W2779054585","https://openalex.org/W2808071176","https://openalex.org/W2997056851","https://openalex.org/W2997591391","https://openalex.org/W3021083751","https://openalex.org/W3034655362","https://openalex.org/W3042724941","https://openalex.org/W3047058320","https://openalex.org/W3089915566","https://openalex.org/W3100245404","https://openalex.org/W3107070550","https://openalex.org/W3115950764","https://openalex.org/W3119397537","https://openalex.org/W3170841864","https://openalex.org/W6739901393","https://openalex.org/W6745740328","https://openalex.org/W6766322091","https://openalex.org/W6784581610","https://openalex.org/W6789705400"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"High-resolution":[0],"remote":[1,11,18,42,85,116,181],"sensing":[2,12,19,43,86,117,182],"images":[3,31],"are":[4,47],"now":[5],"available":[6],"with":[7,80,123],"the":[8,34,63,81,124,136,139,166,173,188,195,198],"progress":[9],"of":[10,65,83,161,168,197],"technology.":[13],"With":[14],"respect":[15],"to":[16,74,95,121,152,156,179],"popular":[17],"tasks":[20],"like":[21],"scene":[22,149],"classification,":[23],"image":[24,35,44,118,157,183],"captioning":[25,45,158],"provides":[26],"comprehensible":[27],"information":[28],"about":[29],"such":[30,66],"by":[32,103],"summarizing":[33],"content":[36],"in":[37,105,138,207],"human-readable":[38],"text.":[39],"Most":[40],"existing":[41],"methods":[46],"based":[48],"on":[49,187],"deep":[50],"learning-based":[51],"encoder-decoder":[52,114],"frameworks,":[53],"using":[54],"Convolutional":[55],"Neural":[56,60],"Network":[57,61],"or":[58],"Recurrent":[59],"as":[62,112],"backbone":[64],"frameworks.":[67],"Such":[68],"frameworks":[69],"show":[70,194],"a":[71,110],"limited":[72,125],"capability":[73,160],"analyze":[75],"sequential":[76],"data":[77,192],"and":[78,159],"cope":[79],"lack":[82],"captioned":[84],"training":[87,126,140],"images.":[88],"Recently":[89],"introduced":[90],"Transformer":[91,111],"architecture":[92],"exploits":[93],"self-attention":[94],"obtain":[96],"superior":[97],"performance":[98],"for":[99,115,147],"sequence-analysis":[100],"tasks.":[101],"Inspired":[102],"this,":[104],"this":[106,171],"work,":[107],"we":[108],"employ":[109],"an":[113,128],"captioning.":[119,184],"Moreover,":[120],"deal":[122],"data,":[127],"auxiliary":[129,143],"decoder":[130,144],"is":[131,145,172],"used":[132],"that":[133],"further":[134],"helps":[135],"encoder":[137],"process.":[141],"The":[142,201],"trained":[146],"multi-label":[148,177],"classification":[150,178],"due":[151],"its":[153],"conceptual":[154],"similarity":[155],"highlighting":[162],"semantic":[163],"classes.":[164],"To":[165],"best":[167],"our":[169],"knowledge,":[170],"first":[174],"work":[175],"exploiting":[176],"improve":[180],"Experimental":[185],"results":[186],"UC":[189],"Merced":[190],"caption":[191],"set":[193],"efficacy":[196],"proposed":[199],"method.":[200],"implementation":[202],"details":[203],"can":[204],"be":[205],"found":[206],"https://gitlab.lrz.de/ai4eo/captioningMultilabel.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}