{"id":"https://openalex.org/W4414693583","doi":"https://doi.org/10.1109/jstars.2025.3616330","title":"Could Describe Anything Model Understand Remote Sensing Objects?","display_name":"Could Describe Anything Model Understand Remote Sensing Objects?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414693583","doi":"https://doi.org/10.1109/jstars.2025.3616330"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2025.3616330","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3616330","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/jstars.2025.3616330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114246406","display_name":"Ziyi Gao","orcid":"https://orcid.org/0009-0009-9262-8332"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Gao","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0009-9262-8332","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077549875","display_name":"Shuzhou Sun","orcid":"https://orcid.org/0000-0001-8453-3346"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhou Sun","raw_affiliation_strings":["Department of Computer Science & Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8453-3346","affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["TKLNDST, College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5550-8758","affiliations":[{"raw_affiliation_string":"TKLNDST, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087910440","display_name":"Yunli Long","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunli Long","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0004-6095-5965","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101767884","display_name":"Yongxiang Liu","orcid":"https://orcid.org/0000-0003-0364-0137"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiang Liu","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-2011-2873","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29951215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"26586","last_page":"26598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9006999731063843,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9006999731063843,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7605999708175659},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.517799973487854},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5002999901771545},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46309998631477356},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.4584999978542328},{"id":"https://openalex.org/keywords/synthetic-aperture-radar","display_name":"Synthetic aperture radar","score":0.43549999594688416},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3779999911785126},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.37450000643730164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212000131607056},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7605999708175659},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.6166999936103821},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25589999556541443},{"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":"doi:10.1109/jstars.2025.3616330","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3616330","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:52efe893cc54415ab9024c7545fd482a","is_oa":true,"landing_page_url":"https://doaj.org/article/52efe893cc54415ab9024c7545fd482a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 18, Pp 26586-26598 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2025.3616330","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3616330","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5747617250","display_name":null,"funder_award_id":"62531026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7774348999","display_name":null,"funder_award_id":"62376283","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W62621907","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1969616664","https://openalex.org/W2194775991","https://openalex.org/W2255466643","https://openalex.org/W2603566245","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2911584214","https://openalex.org/W3200733355","https://openalex.org/W4211112734","https://openalex.org/W4246193833","https://openalex.org/W4307939578","https://openalex.org/W4390874575","https://openalex.org/W4391376377","https://openalex.org/W4394007658","https://openalex.org/W4394938913","https://openalex.org/W4399399400","https://openalex.org/W4402667899","https://openalex.org/W4402753807","https://openalex.org/W4402753899","https://openalex.org/W4402816732","https://openalex.org/W4402996499","https://openalex.org/W4405769242","https://openalex.org/W4406921704","https://openalex.org/W4406982839","https://openalex.org/W4407619051","https://openalex.org/W4408182599","https://openalex.org/W4409383105","https://openalex.org/W4410226950","https://openalex.org/W4410393822","https://openalex.org/W4410808562","https://openalex.org/W4413754737","https://openalex.org/W4414230494"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"image":[1],"captioning":[2,101,204],"for":[3,14,48,99,202,210],"Remote":[4],"Sensing":[5],"Images":[6],"(RSIs)":[7],"remains":[8],"an":[9],"underexplored":[10],"yet":[11],"crucial":[12],"task":[13],"multimodal":[15,154,214],"scene":[16],"understanding,":[17],"especially":[18],"in":[19,73,102,180,198,217],"domains":[20],"where":[21,185],"localized":[22,100],"semantic":[23],"interpretation":[24],"is":[25,146],"essential.":[26],"However,":[27],"the":[28,52,89,94,107,218],"heterogeneous":[29],"nature":[30],"of":[31,54,93,109,122],"remote":[32,103,219],"sensing":[33,220],"data\u2014spanning":[34],"modalities":[35,137],"such":[36],"as":[37],"visible":[38,170],"light,":[39],"infrared,":[40],"and":[41,131,153,159,182,205,212],"Synthetic":[42],"Aperture":[43],"Radar":[44],"(SAR)\u2014poses":[45],"significant":[46,177],"challenges":[47],"generalization,":[49],"particularly":[50],"under":[51],"lack":[53],"sentence-level":[55],"annotations.":[56],"Existing":[57],"vision-language":[58],"models,":[59],"primarily":[60],"trained":[61],"on":[62,169],"natural":[63],"imagetext":[64],"pairs,":[65],"often":[66],"fail":[67],"to":[68,76,81],"capture":[69],"spatially":[70],"grounded":[71],"semantics":[72],"RSIs,":[74],"leading":[75],"degraded":[77],"performance":[78,178],"when":[79],"transferred":[80],"non-natural":[82],"domains.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87,112],"present":[88],"first":[90],"systematic":[91],"evaluation":[92],"Describe":[95],"Anything":[96],"Model":[97],"(DAM)":[98],"sensing.":[104],"To":[105],"address":[106],"scarcity":[108],"aligned":[110],"supervision,":[111],"construct":[113],"a":[114,139,195,207],"weakly":[115],"supervised":[116],"benchmark":[117,193],"framework":[118],"featuring":[119],"three":[120,136],"levels":[121],"region-of-interest":[123],"prompting":[124],"(full":[125],"image,":[126],"center":[127],"point,":[128],"bounding":[129],"box),":[130],"harmonize":[132],"test":[133],"data":[134],"across":[135],"with":[138,172],"unified":[140,208],"object":[141],"category":[142],"(ship).":[143],"Caption":[144],"quality":[145],"assessed":[147],"through":[148],"both":[149],"linguistic":[150],"diversity":[151],"metrics":[152],"alignment":[155],"indicators,":[156],"including":[157],"CLIP":[158],"RemoteCLIP":[160],"scores.":[161],"Experimental":[162],"results":[163],"reveal":[164],"that":[165],"DAM":[166],"performs":[167],"robustly":[168],"imagery":[171],"fine-grained":[173],"prompts,":[174],"but":[175],"exhibits":[176],"degradation":[179],"infrared":[181],"SAR":[183],"domains,":[184],"modality-specific":[186],"distortions":[187],"hinder":[188],"effective":[189],"spatial":[190],"grounding.":[191],"Our":[192],"exposes":[194],"critical":[196],"bottleneck":[197],"current":[199],"foundation":[200],"models":[201],"cross-modality":[203],"establishes":[206],"testbed":[209],"evaluating":[211],"improving":[213],"language":[215],"understanding":[216],"field":[221]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}