{"id":"https://openalex.org/W6929136752","doi":"https://doi.org/10.48550/arxiv.2501.08114","title":"Change Captioning in Remote Sensing: Evolution to SAT-Cap -- A Single-Stage Transformer Approach","display_name":"Change Captioning in Remote Sensing: Evolution to SAT-Cap -- A Single-Stage Transformer Approach","publication_year":2025,"publication_date":"2025-01-14","ids":{"openalex":"https://openalex.org/W6929136752","doi":"https://doi.org/10.48550/arxiv.2501.08114"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2501.08114","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08114","pdf_url":"https://arxiv.org/pdf/2501.08114","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.08114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wang, Yuduo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2801798921","display_name":"Helmholtz-Zentrum Dresden-Rossendorf","ror":"https://ror.org/01zy2cs03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801798921"]},{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]},{"id":"https://openalex.org/I4210148560","display_name":"Helmholtz Institute Freiberg for Resource Technology","ror":"https://ror.org/04kdb0j04","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801798921","https://openalex.org/I4210148560"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wang, Yuduo","raw_affiliation_strings":["Helmholtz-Zentrum Dresden-Rossendorf (HZDR) , 09599 Freiberg , Germany","Humboldt-Universit\u00e4t zu Berlin , 10099 Berlin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz-Zentrum Dresden-Rossendorf (HZDR) , 09599 Freiberg , Germany","institution_ids":["https://openalex.org/I2801798921","https://openalex.org/I4210148560"]},{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin , 10099 Berlin , Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu, Weikang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2801798921","display_name":"Helmholtz-Zentrum Dresden-Rossendorf","ror":"https://ror.org/01zy2cs03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801798921"]},{"id":"https://openalex.org/I4210148560","display_name":"Helmholtz Institute Freiberg for Resource Technology","ror":"https://ror.org/04kdb0j04","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801798921","https://openalex.org/I4210148560"]},{"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":"Yu, Weikang","raw_affiliation_strings":["Helmholtz-Zentrum Dresden-Rossendorf (HZDR) , 09599 Freiberg , Germany","Technical University of Munich , 80333 Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz-Zentrum Dresden-Rossendorf (HZDR) , 09599 Freiberg , Germany","institution_ids":["https://openalex.org/I2801798921","https://openalex.org/I4210148560"]},{"raw_affiliation_string":"Technical University of Munich , 80333 Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074919292","display_name":"Pedram Ghamisi","orcid":"https://orcid.org/0000-0003-1203-741X","observed_orcids":["https://orcid.org/0000-0003-1203-741X"]},"institutions":[{"id":"https://openalex.org/I2801798921","display_name":"Helmholtz-Zentrum Dresden-Rossendorf","ror":"https://ror.org/01zy2cs03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801798921"]},{"id":"https://openalex.org/I4210148560","display_name":"Helmholtz Institute Freiberg for Resource Technology","ror":"https://ror.org/04kdb0j04","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801798921","https://openalex.org/I4210148560"]},{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Ghamisi, Pedram","raw_affiliation_strings":["Helmholtz-Zentrum Dresden-Rossendorf (HZDR) , 09599 Freiberg , Germany","Lancaster University , LA1 4YR Lancaster , U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz-Zentrum Dresden-Rossendorf (HZDR) , 09599 Freiberg , Germany","institution_ids":["https://openalex.org/I2801798921","https://openalex.org/I4210148560"]},{"raw_affiliation_string":"Lancaster University , LA1 4YR Lancaster , U.K","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13890","display_name":"Remote Sensing and Land Use","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/change-captioning","display_name":"change captioning","score":0.9769999980926514},{"id":"https://openalex.org/keywords/multitemporal-imagery","display_name":"multi-temporal imagery","score":0.9039999842643738},{"id":"https://openalex.org/keywords/transformer-encoder","display_name":"Transformer encoder","score":0.7360000014305115},{"id":"https://openalex.org/keywords/channel-and-spatial-attention","display_name":"channel and spatial attention","score":0.9559999704360962}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8867999911308289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595999836921692},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5896999835968018},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45680001378059387},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2501.08114","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08114","pdf_url":"https://arxiv.org/pdf/2501.08114","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.08114","doi":"https://doi.org/10.48550/arxiv.2501.08114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.08114","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.08114","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08114","pdf_url":"https://arxiv.org/pdf/2501.08114","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.5351999998092651,"id":"https://metadata.un.org/sdg/13"}],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.5405425429344177,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6929136752.pdf","grobid_xml":"https://content.openalex.org/works/W6929136752.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Change":[0],"captioning":[1,28],"has":[2],"become":[3],"essential":[4],"for":[5,73,117],"accurately":[6],"describing":[7],"changes":[8],"in":[9,45,102,134,151],"multi-temporal":[10,152],"remote":[11,74,153],"sensing":[12,75,154],"data,":[13],"providing":[14],"an":[15],"intuitive":[16],"way":[17],"to":[18,38,49,95,145],"monitor":[19],"Earth's":[20],"dynamics":[21],"through":[22],"natural":[23],"language.":[24],"However,":[25],"existing":[26],"change":[27,76],"methods":[29],"face":[30],"two":[31],"key":[32],"challenges:":[33],"high":[34],"computational":[35],"demands":[36],"due":[37,48],"multistage":[39],"fusion":[40,72,101,106,115],"strategy,":[41],"and":[42,90,105,131,172,184],"insufficient":[43],"detail":[44],"object":[46],"descriptions":[47],"limited":[50],"semantic":[51,147],"extraction":[52],"from":[53,149],"individual":[54],"images.":[55,155],"To":[56],"solve":[57],"these":[58],"challenges,":[59],"we":[60],"propose":[61],"SAT-Cap":[62,80,108],"based":[63],"on":[64,168,174],"the":[65,121,124,142,159,169,175],"transformers":[66],"model":[67,125],"with":[68],"a":[69,82,86,91,111],"single-stage":[70],"feature":[71],"captioning.":[77],"In":[78],"particular,":[79],"integrates":[81],"Spatial-Channel":[83,135],"Attention":[84,136],"Encoder,":[85,137],"Difference-Guided":[87],"Fusion":[88],"module,":[89,107],"Caption":[92],"Decoder.":[93],"Compared":[94],"typical":[96],"models":[97,186],"that":[98],"require":[99],"multi-stage":[100],"transformer":[103],"encoder":[104],"uses":[109],"only":[110],"simple":[112],"cosine":[113],"similarity-based":[114],"module":[116],"information":[118,133,148],"integration,":[119],"reducing":[120],"complexity":[122],"of":[123,161,166],"architecture.":[126],"By":[127],"jointly":[128],"modeling":[129],"spatial":[130],"channel":[132],"our":[138],"approach":[139],"significantly":[140],"enhances":[141],"model's":[143],"ability":[144],"extract":[146],"objects":[150],"Extensive":[156],"experiments":[157],"validate":[158],"effectiveness":[160],"SAT-Cap,":[162],"achieving":[163],"CIDEr":[164],"scores":[165],"140.23%":[167],"LEVIR-CC":[170],"dataset":[171],"97.74%":[173],"DUBAI-CC":[176],"dataset,":[177],"surpassing":[178],"current":[179],"state-of-the-art":[180],"methods.":[181],"The":[182],"code":[183],"pre-trained":[185],"will":[187],"be":[188],"available":[189],"online.":[190]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}