{"id":"https://openalex.org/W4403839058","doi":"https://doi.org/10.3390/rs16213987","title":"A Patch-Level Region-Aware Module with a Multi-Label Framework for Remote Sensing Image Captioning","display_name":"A Patch-Level Region-Aware Module with a Multi-Label Framework for Remote Sensing Image Captioning","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4403839058","doi":"https://doi.org/10.3390/rs16213987"},"language":"en","primary_location":{"id":"doi:10.3390/rs16213987","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16213987","pdf_url":"https://www.mdpi.com/2072-4292/16/21/3987/pdf?version=1730176137","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/16/21/3987/pdf?version=1730176137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047806538","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0003-1985-9256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunpeng Li","raw_affiliation_strings":["Jiangsu Province Engineering Research Center of Integrated Circuit Reliability Technology and Testing System, Wuxi University, Wuxi 214105, China","Jiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, China"],"affiliations":[{"raw_affiliation_string":"Jiangsu Province Engineering Research Center of Integrated Circuit Reliability Technology and Testing System, Wuxi University, Wuxi 214105, China","institution_ids":[]},{"raw_affiliation_string":"Jiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049776440","display_name":"Xiangrong Zhang","orcid":"https://orcid.org/0000-0003-0379-2042"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangrong Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667596","display_name":"Tianyang Zhang","orcid":"https://orcid.org/0000-0001-9079-7970"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyang Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069808220","display_name":"Guanchun Wang","orcid":"https://orcid.org/0000-0002-9606-7052"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanchun Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903875","display_name":"Xinlin Wang","orcid":"https://orcid.org/0000-0003-1224-4611"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlin Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386657","display_name":"Shuo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Li","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100667596"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":0.4815,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65424279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"16","issue":"21","first_page":"3987","last_page":"3987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9842000007629395,"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":0.7642005681991577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117379903793335},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5790503621101379},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5126215815544128},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2999321520328522},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.13029372692108154}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7642005681991577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117379903793335},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5790503621101379},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5126215815544128},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2999321520328522},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.13029372692108154}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/rs16213987","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16213987","pdf_url":"https://www.mdpi.com/2072-4292/16/21/3987/pdf?version=1730176137","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0ec844584a794a23ad6f31a13d854939","is_oa":true,"landing_page_url":"https://doaj.org/article/0ec844584a794a23ad6f31a13d854939","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 16, Iss 21, p 3987 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/rs16213987","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16213987","pdf_url":"https://www.mdpi.com/2072-4292/16/21/3987/pdf?version=1730176137","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1147961060","display_name":null,"funder_award_id":"62276197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2068034455","display_name":null,"funder_award_id":"20232033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5324547038","display_name":null,"funder_award_id":"62171332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5584298476","display_name":null,"funder_award_id":"62006178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5828585638","display_name":null,"funder_award_id":"202413","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403839058.pdf","grobid_xml":"https://content.openalex.org/works/W4403839058.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2098777834","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2774965253","https://openalex.org/W2779054585","https://openalex.org/W2920981979","https://openalex.org/W2939571759","https://openalex.org/W2963351448","https://openalex.org/W2979924880","https://openalex.org/W2995904231","https://openalex.org/W2997056851","https://openalex.org/W3011916860","https://openalex.org/W3015625772","https://openalex.org/W3017628311","https://openalex.org/W3034858767","https://openalex.org/W3046675509","https://openalex.org/W3100245404","https://openalex.org/W3111390112","https://openalex.org/W3117344638","https://openalex.org/W3194015448","https://openalex.org/W3200916265","https://openalex.org/W4200272616","https://openalex.org/W4205659311","https://openalex.org/W4206028074","https://openalex.org/W4206111836","https://openalex.org/W4206470192","https://openalex.org/W4214587440","https://openalex.org/W4220716465","https://openalex.org/W4223896192","https://openalex.org/W4226228401","https://openalex.org/W4226537900","https://openalex.org/W4283216168","https://openalex.org/W4283360854","https://openalex.org/W4285505614","https://openalex.org/W4292258945","https://openalex.org/W4293057149","https://openalex.org/W4310459386","https://openalex.org/W4312915946","https://openalex.org/W4313032421","https://openalex.org/W4320169083","https://openalex.org/W4385864244","https://openalex.org/W4404520795","https://openalex.org/W6800139171","https://openalex.org/W6806282047","https://openalex.org/W6806569910","https://openalex.org/W6806711163","https://openalex.org/W6809415072","https://openalex.org/W6811007873","https://openalex.org/W6839761106","https://openalex.org/W6841348963","https://openalex.org/W6841874561"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Recent":[0],"Transformer-based":[1,24,87],"works":[2],"can":[3],"generate":[4],"high-quality":[5],"captions":[6],"for":[7,27,41,118,167],"remote":[8,42],"sensing":[9,43],"images":[10],"(RSIs).":[11],"However,":[12],"these":[13],"methods":[14],"generally":[15],"feed":[16],"global":[17],"or":[18],"grid":[19],"visual":[20],"features":[21,102,130],"to":[22,58,75,105,138],"a":[23,48,54,63,69],"captioning":[25,45],"model":[26],"associating":[28],"cross-modal":[29],"information,":[30],"which":[31,84,127],"limits":[32],"performance.":[33],"In":[34],"this":[35],"work,":[36],"we":[37,123],"investigate":[38],"unexplored":[39],"ideas":[40],"image":[44,92],"task,":[46],"using":[47],"novel":[49],"patch-level":[50,70],"region-aware":[51,71,107],"module":[52,72],"with":[53],"multi-label":[55,97],"framework.":[56],"Due":[57],"an":[59],"overhead":[60],"perspective":[61],"and":[62,131,142,149,163],"significantly":[64],"larger":[65],"scale":[66],"in":[67,80],"RSIs,":[68],"is":[73,116],"designed":[74],"filter":[76],"the":[77,81,86,95,106,111,120,135,154,160],"redundant":[78],"information":[79],"RSI":[82],"scene,":[83],"benefits":[85],"decoder":[88],"by":[89],"attaining":[90],"improved":[91],"perception.":[93],"Technically,":[94],"trainable":[96],"classifier":[98],"capitalizes":[99],"on":[100,159],"semantic":[101,132,145],"as":[103],"supplementary":[104],"features.":[108],"Moreover,":[109],"modeling":[110],"inner":[112],"relations":[113],"of":[114,156],"inputs":[115],"essential":[117],"understanding":[119],"RSI.":[121],"Thus,":[122],"introduce":[124],"region-oriented":[125],"attention,":[126],"associates":[128],"region":[129],"labels,":[133],"omits":[134],"irrelevant":[136],"regions":[137],"highlight":[139],"relevant":[140],"regions,":[141],"learns":[143],"related":[144],"information.":[146],"Extensive":[147],"qualitative":[148],"quantitative":[150],"experimental":[151],"results":[152],"show":[153],"superiority":[155],"our":[157,168],"approach":[158],"RSICD,":[161],"UCM-Captions,":[162],"Sydney-Captions.":[164],"The":[165],"code":[166],"method":[169],"will":[170],"be":[171],"publicly":[172],"available.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}