{"id":"https://openalex.org/W4404316994","doi":"https://doi.org/10.1109/tgrs.2024.3497338","title":"Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance","display_name":"Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404316994","doi":"https://doi.org/10.1109/tgrs.2024.3497338"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3497338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3497338","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.14032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106414781","display_name":"Yongshuo Zhu","orcid":"https://orcid.org/0009-0002-6123-3775"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongshuo Zhu","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6123-3775","affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386343","display_name":"Lu Li","orcid":"https://orcid.org/0000-0003-0465-2340"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Li","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0465-2340","affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101518544","display_name":"Keyan Chen","orcid":"https://orcid.org/0000-0003-0483-1306"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyan Chen","raw_affiliation_strings":["Image Processing Center, School of Astronautics, and the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0483-1306","affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, and the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059677848","display_name":"Chenyang Liu","orcid":"https://orcid.org/0000-0003-3034-6646"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Liu","raw_affiliation_strings":["Image Processing Center, School of Astronautics, and the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3034-6646","affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, and the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016025633","display_name":"Fugen Zhou","orcid":"https://orcid.org/0000-0002-9933-7388"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fugen Zhou","raw_affiliation_strings":["Image Processing Center, School of Astronautics, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9933-7388","affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058849690","display_name":"Zhenwei Shi","orcid":"https://orcid.org/0000-0002-4772-3172"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenwei Shi","raw_affiliation_strings":["Image Processing Center, School of Astronautics, and the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4772-3172","affiliations":[{"raw_affiliation_string":"Image Processing Center, School of Astronautics, and the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":3.5725,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94575929,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.983299970626831,"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":0.983299970626831,"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":0.9704999923706055,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9466000199317932,"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":0.8059773445129395},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7925747632980347},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5820208191871643},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.5314705967903137},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43584805727005005},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.40106111764907837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3954041004180908},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3814738392829895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3639093339443207},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.3516393303871155},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3440585136413574},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08810073137283325},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08085262775421143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8059773445129395},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7925747632980347},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5820208191871643},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.5314705967903137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43584805727005005},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.40106111764907837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3954041004180908},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3814738392829895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3639093339443207},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3516393303871155},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3440585136413574},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08810073137283325},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08085262775421143}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tgrs.2024.3497338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3497338","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"},{"id":"pmh:oai:arXiv.org:2407.14032","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.14032","pdf_url":"https://arxiv.org/pdf/2407.14032","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,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.14032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.14032","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,"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:2407.14032","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.14032","pdf_url":"https://arxiv.org/pdf/2407.14032","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,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1468938755","display_name":null,"funder_award_id":"JL23005","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"},{"id":"https://openalex.org/G3221306437","display_name":null,"funder_award_id":"62271018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7969261120","display_name":null,"funder_award_id":"623B2013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8320858330","display_name":null,"funder_award_id":"62125102","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"},{"id":"https://openalex.org/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404316994.pdf","grobid_xml":"https://content.openalex.org/works/W4404316994.grobid-xml"},"referenced_works_count":98,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2053381674","https://openalex.org/W2407776548","https://openalex.org/W2891248708","https://openalex.org/W2902594250","https://openalex.org/W2908510526","https://openalex.org/W2910587630","https://openalex.org/W2963430933","https://openalex.org/W2963842982","https://openalex.org/W2988020997","https://openalex.org/W3003247314","https://openalex.org/W3004423752","https://openalex.org/W3009942016","https://openalex.org/W3017628311","https://openalex.org/W3027225766","https://openalex.org/W3034225195","https://openalex.org/W3085046840","https://openalex.org/W3099503507","https://openalex.org/W3120611686","https://openalex.org/W3141797743","https://openalex.org/W3168867926","https://openalex.org/W3171125843","https://openalex.org/W3176470992","https://openalex.org/W3180045188","https://openalex.org/W3207627484","https://openalex.org/W3208912750","https://openalex.org/W3209698263","https://openalex.org/W3211329537","https://openalex.org/W3217456364","https://openalex.org/W4206591456","https://openalex.org/W4211112734","https://openalex.org/W4213124617","https://openalex.org/W4213455776","https://openalex.org/W4283776488","https://openalex.org/W4286238700","https://openalex.org/W4288391486","https://openalex.org/W4289537913","https://openalex.org/W4292348104","https://openalex.org/W4312364622","https://openalex.org/W4312446817","https://openalex.org/W4312549298","https://openalex.org/W4312795296","https://openalex.org/W4313021481","https://openalex.org/W4313476697","https://openalex.org/W4313591171","https://openalex.org/W4362598957","https://openalex.org/W4366850747","https://openalex.org/W4367721767","https://openalex.org/W4384787738","https://openalex.org/W4385436442","https://openalex.org/W4386065383","https://openalex.org/W4386825420","https://openalex.org/W4386839901","https://openalex.org/W4387350510","https://openalex.org/W4387402974","https://openalex.org/W4387802245","https://openalex.org/W4387885876","https://openalex.org/W4390872223","https://openalex.org/W4390874575","https://openalex.org/W4391021462","https://openalex.org/W4391559729","https://openalex.org/W4391892563","https://openalex.org/W4392909631","https://openalex.org/W4394938913","https://openalex.org/W4398249074","https://openalex.org/W4399154429","https://openalex.org/W4399344797","https://openalex.org/W4399455321","https://openalex.org/W4400489056","https://openalex.org/W4400810737","https://openalex.org/W4401357939","https://openalex.org/W4402260637","https://openalex.org/W4402261590","https://openalex.org/W4402473945","https://openalex.org/W4402713111","https://openalex.org/W4402727764","https://openalex.org/W4402776460","https://openalex.org/W6682631176","https://openalex.org/W6685145238","https://openalex.org/W6713582272","https://openalex.org/W6757817989","https://openalex.org/W6763070779","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6806810910","https://openalex.org/W6810334672","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852874933","https://openalex.org/W6853638429","https://openalex.org/W6854878091","https://openalex.org/W6857012850","https://openalex.org/W6859801230","https://openalex.org/W6860096759","https://openalex.org/W6869812824","https://openalex.org/W6876332386","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4285238471","https://openalex.org/W2359143405","https://openalex.org/W2537839963","https://openalex.org/W2111235920","https://openalex.org/W2059508983","https://openalex.org/W2022357542","https://openalex.org/W1546139022","https://openalex.org/W2013055153","https://openalex.org/W4252741181","https://openalex.org/W2349698472"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,18],"image":[2],"change":[3,48,54,95,102,140,152,209],"captioning":[4,55],"(RSICC)":[5],"aims":[6],"to":[7,133,150,156],"articulate":[8],"the":[9,24,60,72,82,145,158,161,183,187,196],"changes":[10],"in":[11,30,42],"objects":[12],"of":[13,26,74,85,160,164,198],"interest":[14],"within":[15],"bitemporal":[16,109],"remote":[17],"images":[19],"using":[20],"natural":[21],"language.":[22],"Given":[23],"limitations":[25],"current":[27],"RSICC":[28],"methods":[29],"expressing":[31],"general":[32],"features":[33],"across":[34,215],"multitemporal":[35],"and":[36,39,46,63,88,93,138,166,189,200,211],"spatial":[37],"scenarios,":[38],"their":[40],"deficiency":[41],"providing":[43],"granular,":[44],"robust,":[45],"precise":[47],"descriptions,":[49],"we":[50,67,106,168],"introduce":[51],"a":[52,108,116,128,139,170],"novel":[53],"(CC)":[56],"method":[57,185],"based":[58,143],"on":[59,77,144,186],"foundational":[61],"knowledge":[62,84],"semantic":[64,118,136],"guidance,":[65],"which":[66],"term":[68],"Semantic-CC.":[69],"Semantic-CC":[70,204],"alleviates":[71],"dependency":[73],"high-generalization":[75],"algorithms":[76],"extensive":[78],"annotations":[79],"by":[80,98],"harnessing":[81],"latent":[83],"foundation":[86],"models,":[87],"it":[89],"generates":[90],"more":[91,207],"comprehensive":[92],"accurate":[94,208],"descriptions":[96,210],"guided":[97],"pixel-level":[99,135],"semantics":[100],"from":[101],"detection":[103],"(CD).":[104],"Specifically,":[105],"propose":[107,169],"SAM-based":[110],"encoder":[111],"for":[112,121],"dual-image":[113],"feature":[114],"extraction;":[115],"multitask":[117],"aggregation":[119],"neck":[120],"facilitating":[122],"information":[123],"interaction":[124],"between":[125],"heterogeneous":[126],"tasks;":[127],"straightforward":[129],"multiscale":[130],"CD":[131,165,199],"decoder":[132,142],"provide":[134],"guidance;":[137],"caption":[141],"large":[146],"language":[147],"model":[148],"(LLM)":[149],"generate":[151,206],"description":[153],"sentences.":[154],"Moreover,":[155],"ensure":[157],"stability":[159],"joint":[162],"training":[163,172],"CC,":[167,201],"three-stage":[171],"strategy":[173],"that":[174,203],"supervises":[175],"different":[176],"tasks":[177],"at":[178],"various":[179],"stages.":[180],"We":[181],"validate":[182],"proposed":[184],"LEVIR-CC":[188],"LEVIR-CD":[190],"datasets.":[191],"The":[192],"experimental":[193],"results":[194],"corroborate":[195],"complementarity":[197],"demonstrating":[202],"can":[205],"achieve":[212],"optimal":[213],"performance":[214],"both":[216],"tasks.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}