{"id":"https://openalex.org/W4391305855","doi":"https://doi.org/10.1109/tgrs.2024.3359316","title":"Bootstrapping Interactive Image\u2013Text Alignment for Remote Sensing Image Captioning","display_name":"Bootstrapping Interactive Image\u2013Text Alignment for Remote Sensing Image Captioning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391305855","doi":"https://doi.org/10.1109/tgrs.2024.3359316"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3359316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3359316","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037082005","display_name":"Cong Yang","orcid":"https://orcid.org/0000-0002-8314-0935"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210125402","display_name":"Hubei Zhongshan Hospital","ror":"https://ror.org/02xhgjz70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210125402"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Yang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","Hubei Luojia Laboratory, Wuhan, P. R. China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Hubei Luojia Laboratory, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210125402"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002584135","display_name":"Zuchao Li","orcid":"https://orcid.org/0000-0003-0436-8446"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210125402","display_name":"Hubei Zhongshan Hospital","ror":"https://ror.org/02xhgjz70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210125402"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuchao Li","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","Hubei Luojia Laboratory, Wuhan, P. R. China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Hubei Luojia Laboratory, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210125402"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024278302","display_name":"Lefei Zhang","orcid":"https://orcid.org/0000-0003-0542-2280"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210125402","display_name":"Hubei Zhongshan Hospital","ror":"https://ror.org/02xhgjz70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210125402"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lefei Zhang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","Hubei Luojia Laboratory, Wuhan, P. R. China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-0542-2280","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Hubei Luojia Laboratory, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210125402"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6064,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.98796025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9948999881744385,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9876000285148621,"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/computer-science","display_name":"Computer science","score":0.8411833047866821},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8084928393363953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088605880737305},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.46181806921958923},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.44880205392837524},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4400044083595276},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41995736956596375},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4179673194885254},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4142621159553528},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.30043885111808777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411833047866821},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8084928393363953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088605880737305},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.46181806921958923},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.44880205392837524},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4400044083595276},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41995736956596375},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4179673194885254},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4142621159553528},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30043885111808777},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3359316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3359316","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7684016204","display_name":null,"funder_award_id":"62122060","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2412588858","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2774965253","https://openalex.org/W2779054585","https://openalex.org/W2896457183","https://openalex.org/W2911584214","https://openalex.org/W2995904231","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3014611590","https://openalex.org/W3015625772","https://openalex.org/W3038038411","https://openalex.org/W3040902738","https://openalex.org/W3046260628","https://openalex.org/W3091588028","https://openalex.org/W3097754216","https://openalex.org/W3100245404","https://openalex.org/W3117344638","https://openalex.org/W3124566001","https://openalex.org/W3154766321","https://openalex.org/W3162090017","https://openalex.org/W3170092793","https://openalex.org/W3173220247","https://openalex.org/W3194015448","https://openalex.org/W3196922338","https://openalex.org/W4206111836","https://openalex.org/W4213449032","https://openalex.org/W4214587440","https://openalex.org/W4221147537","https://openalex.org/W4225630686","https://openalex.org/W4229005866","https://openalex.org/W4231896027","https://openalex.org/W4283155340","https://openalex.org/W4289537913","https://openalex.org/W4292828275","https://openalex.org/W4292968451","https://openalex.org/W4293508747","https://openalex.org/W4307653761","https://openalex.org/W4310459386","https://openalex.org/W4313476697","https://openalex.org/W4318718936","https://openalex.org/W4323929084","https://openalex.org/W4379382429","https://openalex.org/W4380763457","https://openalex.org/W4385245566","https://openalex.org/W4385571886","https://openalex.org/W4394966885","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6766904570","https://openalex.org/W6775188310","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6791776128","https://openalex.org/W6795072802","https://openalex.org/W6797578546","https://openalex.org/W6800139874","https://openalex.org/W6810334672","https://openalex.org/W6811340617","https://openalex.org/W6849177959","https://openalex.org/W6852403328"],"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":{"Recently,":[0],"remote":[1,11,23,39,76,96,115,127,147],"sensing":[2,12,24,40,77,97,116,128,148],"image":[3,41,78,169],"captioning":[4],"has":[5],"gained":[6],"significant":[7,17],"attention":[8],"in":[9,19,28,103,118],"the":[10,16,35,48,60,85,104,119,124,132,144,151,159,162,167,185,194,200],"community.":[13],"Due":[14],"to":[15,70,93,183],"differences":[18],"spatial":[20],"resolution":[21],"of":[22,38,87,110,114,126],"images,":[25],"existing":[26],"methods":[27],"this":[29],"field":[30],"have":[31],"predominantly":[32],"concentrated":[33],"on":[34,84],"fine-grained":[36],"extraction":[37],"features,":[42],"but":[43],"they":[44],"cannot":[45],"effectively":[46],"handle":[47],"semantic":[49],"consistency":[50],"between":[51],"visual":[52,129,190],"features":[53,113,149],"and":[54,197],"textual":[55,156],"features.":[56,99,130,157,191],"To":[57],"efficiently":[58],"align":[59,95],"image-text,":[61],"we":[62],"propose":[63],"a":[64,88,172],"novel":[65],"two-stage":[66],"vision-language":[67],"pre-training-based":[68],"approach":[69],"bootstrap":[71],"interactive":[72,90,105,152,163],"image-text":[73,98,139],"alignment":[74,137],"for":[75],"captioning,":[79],"called":[80],"BITA,":[81],"which":[82,142],"relies":[83],"design":[86],"lightweight":[89],"Fourier":[91,101,106,153,164],"Transformer":[92,107,154,165],"better":[94],"The":[100,212],"layer":[102],"is":[108,181,214],"capable":[109],"extracting":[111],"multi-scale":[112,146],"images":[117],"frequency":[120],"domain,":[121],"thereby":[122],"reducing":[123],"redundancy":[125],"Specifically,":[131],"first":[133],"stage":[134],"involves":[135],"preliminary":[136],"through":[138],"contrastive":[140],"learning,":[141],"aligns":[143],"learned":[145],"from":[150],"with":[155,171],"In":[158],"second":[160],"stage,":[161],"connects":[166],"frozen":[168],"encoder":[170],"large":[173],"language":[174,179],"model.":[175],"Then,":[176],"prefix":[177],"causal":[178],"modeling":[180],"utilized":[182],"guide":[184],"text":[186],"generation":[187],"process":[188],"using":[189],"Ultimately,":[192],"across":[193],"UCM-caption,":[195],"RSICD,":[196],"NWPU-caption":[198],"datasets,":[199],"experimental":[201],"results":[202],"clearly":[203],"demonstrate":[204],"that":[205],"BITA":[206],"outperforms":[207],"other":[208],"advanced":[209],"comparative":[210],"approaches.":[211],"code":[213],"available":[215],"at":[216],"https://github.com/yangcong356/BITA.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":18}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}