{"id":"https://openalex.org/W4415538350","doi":"https://doi.org/10.1145/3746027.3754559","title":"GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing","display_name":"GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538350","doi":"https://doi.org/10.1145/3746027.3754559"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754559","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5101737703","display_name":"X. T. Ma","orcid":"https://orcid.org/0009-0007-4909-0894"},"institutions":[{"id":"https://openalex.org/I4210111801","display_name":"Space Frontier Foundation","ror":"https://ror.org/027pcre83","country_code":"US","type":"other","lineage":["https://openalex.org/I4210111801"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianzhi Ma","raw_affiliation_strings":["Institute of Space Earth Science, School of Frontier Sciences, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-4909-0894","affiliations":[{"raw_affiliation_string":"Institute of Space Earth Science, School of Frontier Sciences, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I4210111801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372619","display_name":"Jianhui Li","orcid":"https://orcid.org/0009-0001-6253-9808"},"institutions":[{"id":"https://openalex.org/I4210111801","display_name":"Space Frontier Foundation","ror":"https://ror.org/027pcre83","country_code":"US","type":"other","lineage":["https://openalex.org/I4210111801"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianhui Li","raw_affiliation_strings":["Institute of Space Earth Science, School of Frontier Sciences, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-6253-9808","affiliations":[{"raw_affiliation_string":"Institute of Space Earth Science, School of Frontier Sciences, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I4210111801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073273454","display_name":"Changhua Pei","orcid":"https://orcid.org/0000-0001-9288-4787"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhua Pei","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9288-4787","affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458777","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-0411-5396"},"institutions":[{"id":"https://openalex.org/I4210111801","display_name":"Space Frontier Foundation","ror":"https://ror.org/027pcre83","country_code":"US","type":"other","lineage":["https://openalex.org/I4210111801"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Institute of Space Earth Science, School of Frontier Sciences, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0411-5396","affiliations":[{"raw_affiliation_string":"Institute of Space Earth Science, School of Frontier Sciences, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I4210111801"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5441","last_page":"5450"},"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9973999857902527,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9940999746322632,"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/parsing","display_name":"Parsing","score":0.5552999973297119},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.541700005531311},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5311999917030334},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4941999912261963},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4041999876499176},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.4023999869823456},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3571999967098236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789900004863739},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187000036239624},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4941999912261963},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4311999976634979},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3571999967098236},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35499998927116394},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754559","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2333605124","display_name":null,"funder_award_id":"No.491914380007","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2804760775","display_name":null,"funder_award_id":"No.W2412136, No.62202445","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3420756632","display_name":null,"funder_award_id":"No.2022YFB2901800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2515866431","https://openalex.org/W2798556392","https://openalex.org/W2963037989","https://openalex.org/W2995904231","https://openalex.org/W3012111773","https://openalex.org/W3034692043","https://openalex.org/W3038038411","https://openalex.org/W3165084071","https://openalex.org/W4229439310","https://openalex.org/W4285818301","https://openalex.org/W4316661266","https://openalex.org/W4322707256","https://openalex.org/W4377288965","https://openalex.org/W4381049901","https://openalex.org/W4389104899","https://openalex.org/W4392397297","https://openalex.org/W4393906060","https://openalex.org/W4395447356","https://openalex.org/W4399399400","https://openalex.org/W4402473945","https://openalex.org/W4402667899","https://openalex.org/W4403331778","https://openalex.org/W4403780595","https://openalex.org/W4405895891","https://openalex.org/W4407152340"],"related_works":[],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,103,122,130,139,151,179],"Vision-Language":[3],"Models":[4],"(VLMs)":[5],"in":[6,47,168],"remote":[7,96],"sensing":[8,97],"(RS)":[9],"image":[10,98],"understanding":[11],"has":[12],"achieved":[13],"notable":[14],"progress,":[15],"demonstrating":[16],"the":[17,38,86,119,127,136,148],"basic":[18],"ability":[19],"to":[20,32,40,93,183],"recognize":[21],"and":[22,34,44,112,146],"describe":[23],"geographical":[24],"entities.":[25],"However,":[26],"existing":[27,184],"RS-VLMs":[28,52],"are":[29],"mostly":[30],"limited":[31],"image-level":[33],"region-level":[35],"tasks,":[36],"lacking":[37],"capability":[39],"handle":[41],"pixel-level":[42,170],"tasks":[43,171,178],"performing":[45],"poorly":[46],"small-object":[48],"recognition":[49],"scenarios.":[50],"Moreover,":[51],"consume":[53],"significant":[54],"computational":[55,149],"resources":[56],"when":[57],"processing":[58],"high-resolution":[59,153],"RS":[60,154],"images,":[61],"further":[62],"restricting":[63],"their":[64],"practical":[65],"applicability.":[66],"In":[67],"this":[68],"context,":[69],"we":[70],"propose":[71],"GeoMag":[72,83,164],"(Geographical":[73],"Magnifier),":[74],"an":[75],"end-to-end":[76],"general-purpose":[77],"large":[78],"model":[79],"framework":[80],"for":[81],"RS.":[82],"dynamically":[84],"focuses":[85],"attention":[87],"scope":[88],"based":[89],"on":[90,159],"prompt":[91],"semantics":[92],"effectively":[94],"perform":[95],"parsing":[99],"across":[100,177],"multiple":[101],"levels":[102],"granularity.":[104],"This":[105,133],"method":[106],"introduces":[107],"Task-driven":[108],"Multi-granularity":[109],"Resolution":[110],"Adjustment":[111],"Prompt-guided":[113],"Semantic-aware":[114],"Cropping,":[115],"which":[116],"adaptively":[117],"reduce":[118],"spatial":[120],"resolution":[121],"task-irrelevant":[123],"regions":[124],"while":[125],"enhancing":[126],"visual":[128],"representation":[129],"task-relevant":[131],"areas.":[132],"approach":[134],"improves":[135],"model's":[137],"perception":[138],"critical":[140],"target":[141],"regions,":[142],"suppresses":[143],"background":[144],"redundancy,":[145],"reduces":[147],"cost":[150],"interpreting":[152],"imagery.":[155],"Extensive":[156],"comparative":[157],"experiments":[158],"10":[160],"benchmarks":[161],"demonstrate":[162],"that":[163],"not":[165],"only":[166],"excels":[167],"handling":[169],"but":[172],"also":[173],"maintains":[174],"competitive":[175],"performance":[176],"other":[180],"granularities":[181],"compared":[182],"RS-VLMs.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}