{"id":"https://openalex.org/W4412567112","doi":"https://doi.org/10.1109/tip.2025.3589096","title":"Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning","display_name":"Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412567112","doi":"https://doi.org/10.1109/tip.2025.3589096","pmid":"https://pubmed.ncbi.nlm.nih.gov/40694446"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3589096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3589096","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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"]}],"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","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":"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuchao Li","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0436-8446","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026145013","display_name":"Hongzan Jiao","orcid":"https://orcid.org/0000-0002-7048-3293"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzan Jiao","raw_affiliation_strings":["School of Urban Design, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-7048-3293","affiliations":[{"raw_affiliation_string":"School of Urban Design, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084683976","display_name":"Zhi Gao","orcid":"https://orcid.org/0000-0003-3325-1183"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Gao","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3325-1183","affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, 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"]}],"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","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":"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":8.9014,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.98460145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":null,"first_page":"7378","last_page":"7390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9405999779701233,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9405999779701233,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9153000116348267,"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":0.8198457360267639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6650354862213135},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6230517029762268},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.5938112735748291},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5910729169845581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5631182193756104},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5354777574539185},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47406548261642456},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.42447978258132935},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3614695072174072},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1728394329547882},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09042471647262573}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8198457360267639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650354862213135},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6230517029762268},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.5938112735748291},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5910729169845581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631182193756104},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5354777574539185},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47406548261642456},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.42447978258132935},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3614695072174072},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1728394329547882},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09042471647262573},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3589096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3589096","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:40694446","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40694446","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2131151903","display_name":null,"funder_award_id":"42192580","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2642843737","display_name":null,"funder_award_id":"62431020, 42192580, 42192583","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4308293926","display_name":null,"funder_award_id":"42192583","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G457964128","display_name":null,"funder_award_id":"62431020","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":53,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2769613401","https://openalex.org/W2779571083","https://openalex.org/W2891248708","https://openalex.org/W2963430933","https://openalex.org/W2964196083","https://openalex.org/W2969081030","https://openalex.org/W2988981892","https://openalex.org/W3027225766","https://openalex.org/W3036453075","https://openalex.org/W3108170342","https://openalex.org/W3130754787","https://openalex.org/W3154766321","https://openalex.org/W3176470992","https://openalex.org/W3180045188","https://openalex.org/W3182257909","https://openalex.org/W3195588784","https://openalex.org/W3207627484","https://openalex.org/W4206111836","https://openalex.org/W4226361741","https://openalex.org/W4289537913","https://openalex.org/W4304091821","https://openalex.org/W4312364622","https://openalex.org/W4313021481","https://openalex.org/W4313350235","https://openalex.org/W4362598957","https://openalex.org/W4377079808","https://openalex.org/W4384787738","https://openalex.org/W4386299129","https://openalex.org/W4386790226","https://openalex.org/W4387350510","https://openalex.org/W4387802245","https://openalex.org/W4387917939","https://openalex.org/W4389903841","https://openalex.org/W4391021462","https://openalex.org/W4391128738","https://openalex.org/W4391697001","https://openalex.org/W4391992377","https://openalex.org/W4392174060","https://openalex.org/W4392909631","https://openalex.org/W4393157162","https://openalex.org/W4395029188","https://openalex.org/W4396909912","https://openalex.org/W4398249074","https://openalex.org/W4400489056","https://openalex.org/W4400644965","https://openalex.org/W4402727764","https://openalex.org/W4402754134","https://openalex.org/W4402968170","https://openalex.org/W4403780601","https://openalex.org/W4404316994"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","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/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Recently,":[0],"while":[1],"significant":[2],"progress":[3],"has":[4],"been":[5],"made":[6],"in":[7],"remote":[8,40,92],"sensing":[9,41,93],"image":[10,42,94],"change":[11,43,76,80,103,107,113,129,132,168,193],"captioning,":[12,44],"existing":[13],"methods":[14,195],"fail":[15],"to":[16,21,27,56,110,126,144,170],"filter":[17],"out":[18],"areas":[19],"unrelated":[20],"actual":[22],"changes,":[23],"making":[24],"models":[25,65],"susceptible":[26],"irrelevant":[28],"features.":[29],"In":[30],"this":[31],"article,":[32],"we":[33,138,187],"propose":[34],"a":[35,86,96,105,121,140],"novel":[36],"multimodal":[37],"model":[38,54,175],"for":[39,89,100,158],"guided":[45],"by":[46],"Key":[47],"Change":[48],"Features":[49],"and":[50,69,73,115,131,162],"Instruction-tuned":[51],"(KCFI).":[52],"This":[53],"aims":[55],"fully":[57],"leverage":[58],"the":[59,71,146,149,172,177,182,197,201],"intrinsic":[60],"knowledge":[61],"of":[62,75,184],"large":[63,122,173],"language":[64,123,174],"through":[66],"visual":[67,159],"instructions":[68,161],"enhance":[70],"effectiveness":[72,183],"accuracy":[74],"features":[77,169],"using":[78,165],"pixel-level":[79,106],"detection":[81,108,133],"tasks.":[82,151],"Specifically,":[83],"KCFI":[84],"includes":[85],"ViTs":[87],"encoder":[88],"extracting":[90],"bi-temporal":[91],"features,":[95,114],"key":[97,112,167],"feature":[98,156],"perceiver":[99],"identifying":[101],"critical":[102],"areas,":[104],"decoder":[109,118],"constrain":[111],"an":[116],"instruction-tuned":[117],"based":[119],"on":[120,196],"model.":[124],"Moreover,":[125],"ensure":[127],"that":[128,164],"captioning":[130,194],"tasks":[134],"are":[135],"jointly":[136],"optimized,":[137],"employ":[139],"dynamic":[141],"weight-averaging":[142],"strategy":[143],"balance":[145],"losses":[147],"between":[148],"two":[150],"We":[152],"also":[153],"explore":[154],"various":[155],"combinations":[157],"fine-tuning":[160],"demonstrate":[163],"only":[166],"guide":[171],"is":[176],"optimal":[178],"choice.":[179],"To":[180],"validate":[181],"our":[185],"approach,":[186],"compare":[188],"it":[189],"against":[190],"several":[191],"state-of-the-art":[192],"LEVIR-CC":[198],"dataset,":[199],"achieving":[200],"best":[202],"performance.":[203],"Our":[204],"code":[205],"will":[206],"be":[207],"available":[208],"at":[209],"https://github.com/yangcong356/KCFI.git.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":9}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}