{"id":"https://openalex.org/W7123341446","doi":"https://doi.org/10.1109/access.2026.3652136","title":"BCMT: Bidirectional Cross-Modality Transformer for Remote Sensing Image Captioning","display_name":"BCMT: Bidirectional Cross-Modality Transformer for Remote Sensing Image Captioning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123341446","doi":"https://doi.org/10.1109/access.2026.3652136"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3652136","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652136","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3652136","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122895819","display_name":"S G Shivaprasad Yadav","orcid":null},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. G. Shivaprasad Yadav","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, M. S. Ramaiah Institute of Technology, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-7083-0072","affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, M. S. Ramaiah Institute of Technology, Bengaluru, India","institution_ids":["https://openalex.org/I302410947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015785625","display_name":"Satti Sudha Mohan Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009046","display_name":"SRKR Engineering College","ror":"https://ror.org/038qac964","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009046"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Satti Sudha Mohan Reddy","raw_affiliation_strings":["Department of Electronics and Communication Engineering, SRKR Engineering College, Bhimavaram, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, SRKR Engineering College, Bhimavaram, Andhra Pradesh, India","institution_ids":["https://openalex.org/I4400009046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138340869","display_name":"Parameshachari BD","orcid":"https://orcid.org/0000-0002-3997-5070"},"institutions":[{"id":"https://openalex.org/I1333540553","display_name":"Nitte University","ror":"https://ror.org/029nydt37","country_code":"IN","type":"education","lineage":["https://openalex.org/I1333540553"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parameshachari Bidare Divakarachari","raw_affiliation_strings":["Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, Nitte (Deemed to be University), Yelahanka, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-3997-5070","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, Nitte (Deemed to be University), Yelahanka, Bengaluru, India","institution_ids":["https://openalex.org/I1333540553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122891694","display_name":"Ravi Kiran Varma Penmatsa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151968","display_name":"Hindu College of Pharmacy","ror":"https://ror.org/04sadrh19","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210151968"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Kiran Varma Penmatsa","raw_affiliation_strings":["Department of Information Technology, Sagi Rama Krishnam Raju Engineering College, Bhimavaram, Andhra Pradesh, India"],"raw_orcid":"https://orcid.org/0000-0002-4989-1305","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Sagi Rama Krishnam Raju Engineering College, Bhimavaram, Andhra Pradesh, India","institution_ids":["https://openalex.org/I4210151968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002372334","display_name":"Hirald Dwaraka Praveena","orcid":"https://orcid.org/0000-0002-8785-3684"},"institutions":[{"id":"https://openalex.org/I108526665","display_name":"Fakir Mohan University","ror":"https://ror.org/00g0n6t22","country_code":"IN","type":"education","lineage":["https://openalex.org/I108526665"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hirald Dwaraka Praveena","raw_affiliation_strings":["Department of Electronics and Communication Engineering, School of Engineering, Mohan Babu University, Tirupati, Andhra Pradesh, India"],"raw_orcid":"https://orcid.org/0000-0002-8785-3684","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, School of Engineering, Mohan Babu University, Tirupati, Andhra Pradesh, India","institution_ids":["https://openalex.org/I108526665"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.3672,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9086703,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"14","issue":null,"first_page":"12560","last_page":"12578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940000176429749,"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":0.9940000176429749,"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":0.0010000000474974513,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.000699999975040555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9083999991416931},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5623000264167786},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5130000114440918},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.3727000057697296},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3571000099182129},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.336899995803833},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3368000090122223}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9083999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5623000264167786},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5383999943733215},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3727000057697296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36959999799728394},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3125},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2985301230","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite image","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3652136","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652136","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d791980a88ef4459b31a45f16b9be48e","is_oa":false,"landing_page_url":"https://doaj.org/article/d791980a88ef4459b31a45f16b9be48e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 12560-12578 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3652136","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652136","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6131395101547241,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2607508964","https://openalex.org/W4211112734","https://openalex.org/W4213157969","https://openalex.org/W4213449032","https://openalex.org/W4214587440","https://openalex.org/W4220716465","https://openalex.org/W4283216168","https://openalex.org/W4292968451","https://openalex.org/W4293508747","https://openalex.org/W4296280877","https://openalex.org/W4310459386","https://openalex.org/W4312389717","https://openalex.org/W4317433994","https://openalex.org/W4385632800","https://openalex.org/W4385864244","https://openalex.org/W4386003541","https://openalex.org/W4387986561","https://openalex.org/W4389091674","https://openalex.org/W4390539794","https://openalex.org/W4391226826","https://openalex.org/W4391341588","https://openalex.org/W4391935992","https://openalex.org/W4393938311","https://openalex.org/W4394585954","https://openalex.org/W4395041667","https://openalex.org/W4396941249","https://openalex.org/W4398222290","https://openalex.org/W4399571349","https://openalex.org/W4400977318","https://openalex.org/W4401510256","https://openalex.org/W4401754729","https://openalex.org/W4403118446","https://openalex.org/W4403183405","https://openalex.org/W4403864103","https://openalex.org/W4403980953","https://openalex.org/W4404057535","https://openalex.org/W4404563351","https://openalex.org/W4405517129","https://openalex.org/W4414079449"],"related_works":[],"abstract_inverted_index":{"Remote":[0],"sensing":[1,17],"image":[2,93,161],"captioning":[3,162],"(RSIC)":[4],"focuses":[5],"on":[6,100,224],"generating":[7],"natural":[8],"language":[9],"descriptions":[10],"of":[11,22,70,78,103,136,218],"the":[12,68,115,164,184,225],"objects":[13],"seen":[14],"in":[15,28,149],"remote":[16],"images.":[18],"However,":[19],"inefficient":[20,76],"use":[21],"object":[23,79],"texture":[24],"and":[25,36,47,81,89,94,106,125,131,141,203,210,221,228],"semantic":[26,82,181],"features":[27,38,83],"images":[29,35,153,169],"with":[30,110],"insufficient":[31],"cross-modal":[32],"alignment":[33,182],"among":[34,207],"text":[37,95],"affects":[39],"a":[40,59,216],"model\u2019s":[41],"ability":[42],"to":[43,52,66,92,192,199],"generate":[44],"high":[45,167],"quality":[46],"meaningful":[48,71,111],"captions.":[49,72,133],"In":[50],"order":[51],"address":[53],"this":[54,56,150],"challenge,":[55],"research":[57],"proposes":[58],"Bidirectional":[60],"Cross-Modality":[61],"Transformer":[62],"(BCMT)":[63],"for":[64,128,160],"RSIC":[65,236],"ensure":[67],"generation":[69],"The":[73,134,152,174,213],"BCMT":[74,116,175,198,214],"tackles":[75],"usage":[77],"textures":[80,127],"by":[84,183],"efficiently":[85],"applying":[86],"bidirectional":[87,177],"interaction":[88],"cross-attention":[90],"mechanisms":[91],"features.":[96],"It":[97],"dynamically":[98],"focusses":[99],"relevant":[101],"parts":[102],"both":[104],"modalities":[105],"ensures":[107],"fine-grained":[108],"relationships":[109],"feature":[112,119,190],"utilization.":[113],"Furthermore,":[114],"incorporates":[117],"multi-level":[118,189],"fusion":[120,191],"which":[121,196,231],"integrates":[122],"high-level":[123],"semantics":[124],"low-level":[126],"producing":[129],"high-quality":[130],"context-aware":[132,202],"University":[135,144],"California":[137],"Merced":[138],"(UCM),":[139],"Sydney,":[140],"Northwestern":[142],"Polytechnical":[143],"(NWPU)":[145],"datasets":[146,156,230],"are":[147,157],"considered":[148],"research.":[151],"from":[154],"these":[155],"directly":[158],"fed":[159],"as":[163],"dataset":[165],"contains":[166],"resolution":[168],"that":[170],"do":[171],"require":[172],"preprocessing.":[173],"introduces":[176],"cross-modality":[178],"attention,":[179],"cyclic":[180],"Joint":[185],"Representation":[186],"Translator":[187],"(JRT),":[188],"enhance":[193],"visual-textual":[194],"interactions":[195],"provides":[197],"provide":[200],"more":[201],"semantical":[204],"consistent":[205],"captions":[206],"UCM,":[208,226],"Sydney":[209,227],"NWPU":[211,229],"datasets.":[212],"achieves":[215],"B-1":[217],"95.19%,":[219],"92.18%":[220],"94.28%":[222],"respectively":[223],"is":[232],"better":[233],"than":[234],"existing":[235],"models.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-01-14T00:00:00"}