{"id":"https://openalex.org/W4409367667","doi":"https://doi.org/10.1609/aaai.v39i6.32683","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","display_name":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409367667","doi":"https://doi.org/10.1609/aaai.v39i6.32683"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i6.32683","doi":"https://doi.org/10.1609/aaai.v39i6.32683","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i6.32683","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32683/34838","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32683/34838","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chao Pang","orcid":null,"observed_orcids":[]},"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":"Chao Pang","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University\nSchool of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University\nSchool of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071887817","display_name":"Xingxing Weng","orcid":"https://orcid.org/0000-0002-3326-8439","observed_orcids":["https://orcid.org/0000-0002-3326-8439"]},"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":"Xingxing Weng","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101710913","display_name":"Jiang Wu","orcid":"https://orcid.org/0009-0002-2402-0957","observed_orcids":["https://orcid.org/0009-0002-2402-0957","https://orcid.org/0000-0002-2281-043X"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Wu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435414","display_name":"Jiayu Li","orcid":"https://orcid.org/0009-0001-4479-3706","observed_orcids":["https://orcid.org/0009-0001-4479-3706"]},"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":"Jiayu Li","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109780753","display_name":"Yi Liu","orcid":"https://orcid.org/0009-0003-0397-3705","observed_orcids":["https://orcid.org/0009-0003-0397-3705"]},"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":"Yi Liu","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101728761","display_name":"Jiaxing Sun","orcid":"https://orcid.org/0000-0001-9901-8187","observed_orcids":["https://orcid.org/0000-0001-9901-8187","https://orcid.org/0009-0008-2779-8151"]},"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/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Sun","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory\nState Key Lab. of LIESMARS, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory\nState Key Lab. of LIESMARS, Wuhan University","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103285072","display_name":"Weijia Li","orcid":"https://orcid.org/0009-0006-4868-2786","observed_orcids":["https://orcid.org/0009-0006-4868-2786"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijia Li","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071419125","display_name":"Shuai Wang","orcid":"https://orcid.org/0009-0003-8094-2654","observed_orcids":["https://orcid.org/0009-0003-8094-2654"]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039785210","display_name":"Litong Feng","orcid":"https://orcid.org/0000-0002-6716-3520","observed_orcids":["https://orcid.org/0000-0002-6716-3520"]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Litong Feng","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073032922","display_name":"Gui-Song Xia","orcid":"https://orcid.org/0000-0001-7660-6090","observed_orcids":["https://orcid.org/0000-0001-7660-6090"]},"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/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gui-Song Xia","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University\nSchool of Computer Science, Wuhan University\nState Key Lab. of LIESMARS, Wuhan University\nInstitue for Math & AI, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University\nSchool of Computer Science, Wuhan University\nState Key Lab. of LIESMARS, Wuhan University\nInstitue for Math & AI, Wuhan University","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101615091","display_name":"Conghui He","orcid":"https://orcid.org/0000-0001-8697-695X","observed_orcids":["https://orcid.org/0000-0001-8697-695X"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Conghui He","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory\nSenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory\nSenseTime Research","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":30.7025,"has_fulltext":true,"cited_by_count":96,"citation_normalized_percentile":{"value":0.99662341,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"39","issue":"6","first_page":"6381","last_page":"6388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.9965999722480774,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.00139999995008111,"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":0.0005000000237487257,"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/vision-language-models","display_name":"vision-language models","score":0.9049999713897705},{"id":"https://openalex.org/keywords/remote-sensing-image-analysis","display_name":"remote sensing image analysis","score":0.8809999823570251},{"id":"https://openalex.org/keywords/image-text-dataset","display_name":"image-text dataset","score":0.6650000214576721},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.6669999957084656},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.9620000123977661},{"id":"https://openalex.org/keywords/scene-classification","display_name":"scene classification","score":0.949999988079071},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"multi-label classification","score":0.8820000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5459855794906616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49974989891052246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48345741629600525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47551944851875305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3825855851173401},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3360184133052826},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.13974720239639282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v39i6.32683","doi":"https://doi.org/10.1609/aaai.v39i6.32683","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i6.32683","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32683/34838","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.20213","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.20213","pdf_url":"https://arxiv.org/pdf/2403.20213","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.2403.20213","doi":"https://doi.org/10.48550/arxiv.2403.20213","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.20213","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i6.32683","doi":"https://doi.org/10.1609/aaai.v39i6.32683","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i6.32683","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32683/34838","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3965009956","display_name":null,"funder_award_id":"U22B2011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7875021329","display_name":null,"funder_award_id":"62325111","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/W4409367667.pdf","grobid_xml":"https://content.openalex.org/works/W4409367667.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W3206476077","https://openalex.org/W4226456028","https://openalex.org/W4288043195","https://openalex.org/W4386185600","https://openalex.org/W4387723654","https://openalex.org/W4389523832","https://openalex.org/W4390041933","https://openalex.org/W4399759382","https://openalex.org/W4399837358","https://openalex.org/W4402473945","https://openalex.org/W4402727764","https://openalex.org/W4402916392","https://openalex.org/W4404536218","https://openalex.org/W4407152340","https://openalex.org/W4409383105","https://openalex.org/W4415795395"],"related_works":["https://openalex.org/W4415799042","https://openalex.org/W4409383105","https://openalex.org/W4407743259","https://openalex.org/W4416728464","https://openalex.org/W7206160646","https://openalex.org/W4411143162","https://openalex.org/W4395041667","https://openalex.org/W4389714054","https://openalex.org/W4393159564","https://openalex.org/W4402776460"],"abstract_inverted_index":{"This":[0,75,116],"paper":[1],"develops":[2],"a":[3,20,54],"Versatile":[4],"and":[5,30,38,58,71,86,150,168],"Honest":[6],"vision":[7,138],"language":[8,139],"Model":[9],"(VHM)":[10],"for":[11],"remote":[12,22,44,83,89,96],"sensing":[13,23,45,84,90,97],"image":[14,50,67],"analysis.":[15],"VHM":[16,79,119,134,154],"is":[17],"built":[18],"on":[19,53,141,158],"large-scale":[21],"image-text":[24,46],"dataset":[25,34],"with":[26],"rich-content":[27],"captions":[28,51,62],"(VersaD),":[29],"an":[31],"honest":[32,169],"instruction":[33,98],"comprising":[35],"both":[36],"factual":[37,103],"deceptive":[39,108],"questions":[40,109],"(HnstD).":[41],"Unlike":[42],"prevailing":[43],"datasets,":[47],"in":[48],"which":[49],"focus":[52],"few":[55],"prominent":[56],"objects":[57],"their":[59],"relationships,":[60],"VersaD":[61],"provide":[63],"detailed":[64],"information":[65],"about":[66],"properties,":[68],"object":[69],"attributes,":[70],"the":[72,112],"overall":[73],"scene.":[74],"comprehensive":[76],"captioning":[77],"enables":[78],"to":[80,124],"thoroughly":[81],"understand":[82],"images":[85],"perform":[87],"diverse":[88],"tasks.":[91],"Moreover,":[92],"different":[93],"from":[94,111,120],"existing":[95],"datasets":[99],"that":[100],"only":[101],"include":[102],"questions,":[104],"HnstD":[105],"contains":[106],"additional":[107],"stemming":[110],"non-existence":[113],"of":[114,144],"objects.":[115],"feature":[117],"prevents":[118],"producing":[121],"affirmative":[122],"answers":[123],"nonsense":[125],"queries,":[126],"thereby":[127],"ensuring":[128],"its":[129],"honesty.":[130],"In":[131],"our":[132],"experiments,":[133],"significantly":[135],"outperforms":[136],"various":[137],"models":[140],"common":[142],"tasks":[143],"scene":[145],"classification,":[146],"visual":[147,151],"question":[148,170],"answering,":[149],"grounding.":[152],"Additionally,":[153],"achieves":[155],"competent":[156],"performance":[157],"several":[159],"unexplored":[160],"tasks,":[161],"such":[162],"as":[163],"building":[164],"vectorizing,":[165],"multi-label":[166],"classification":[167],"answering.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":49},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":7}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-04-12T00:00:00"}