{"id":"https://openalex.org/W4415368493","doi":"https://doi.org/10.1109/jstars.2025.3623321","title":"GL-MSIN: A Global\u2013Local Hierarchical Multiscale Interaction Network for Referring Remote Sensing Image Segmentation","display_name":"GL-MSIN: A Global\u2013Local Hierarchical Multiscale Interaction Network for Referring Remote Sensing Image Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415368493","doi":"https://doi.org/10.1109/jstars.2025.3623321"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2025.3623321","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3623321","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":null,"license_id":null,"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.2025.3623321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022144594","display_name":"Wenyu Mi","orcid":"https://orcid.org/0000-0002-4777-5327"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wenyu Mi","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-4777-5327","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":[]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fuzhen Zhuang","orcid":"https://orcid.org/0000-0001-9170-7009"},"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":"Fuzhen Zhuang","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9170-7009","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101587109","display_name":"Jianji Wang","orcid":"https://orcid.org/0000-0002-4284-3933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianji Wang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-4284-3933","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":[]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056061158","display_name":"Le Yu","orcid":"https://orcid.org/0000-0002-4908-3199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Yu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":[]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112915564","display_name":"Boyu Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyu Guo","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":[]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030957641","display_name":"Ruitao Chu","orcid":"https://orcid.org/0009-0009-5667-7882"},"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":"Ruitao Chu","raw_affiliation_strings":["School of Geodesy and Geomatics, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0009-5667-7882","affiliations":[{"raw_affiliation_string":"School of Geodesy and Geomatics, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033808402","display_name":"Meiqin Liu","orcid":"https://orcid.org/0000-0003-0693-6574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meiqin Liu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0003-0693-6574","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":[]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5022144594"],"corresponding_institution_ids":[],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":5.6772,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95854679,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"18","issue":null,"first_page":"27193","last_page":"27207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.972599983215332,"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":0.972599983215332,"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"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9603999853134155,"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/T11106","display_name":"Data Management and Algorithms","score":0.944599986076355,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/segmentation","display_name":"Segmentation","score":0.638700008392334},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6308000087738037},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5956000089645386},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5593000054359436},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.48510000109672546},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4772999882698059},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.383899986743927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8647000193595886},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.638700008392334},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6308000087738037},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5956000089645386},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5397999882698059},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.48510000109672546},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstars.2025.3623321","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3623321","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":null,"license_id":null,"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:8544889bf2a14c33807c3a56f24666c4","is_oa":true,"landing_page_url":"https://doaj.org/article/8544889bf2a14c33807c3a56f24666c4","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 27193-27207 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2025.3623321","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2025.3623321","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":null,"license_id":null,"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/G2051096740","display_name":null,"funder_award_id":"52508037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7207008540","display_name":null,"funder_award_id":"U23A20339","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7950965334","display_name":null,"funder_award_id":"62495091","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8180423952","display_name":null,"funder_award_id":"62125305","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/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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"remote":[1,11,30,97],"sensing":[2,12,31,98],"image":[3,13],"segmentation":[4,72],"aims":[5],"to":[6,53,85,91,109,130,147,170,199],"segment":[7],"objects":[8,21],"in":[9,26,28,66,96,208],"a":[10,16,78,137,142,166,190],"based":[14],"on":[15,254],"natural":[17,239],"language":[18,27,240],"expression.":[19,154],"Identifying":[20],"with":[22,141,242],"uncertain":[23],"quantities":[24],"described":[25],"large-scale":[29],"images":[32],"requires":[33],"enhanced":[34,122],"capabilities":[35],"for":[36],"both":[37],"local":[38,123,132],"detailed":[39],"feature":[40],"extraction":[41,180],"and":[42,149,204,257],"global":[43,143,151,182],"dependency":[44],"perception.":[45],"However,":[46],"the":[47,58,106,121,127,156,162,175,249,255,258],"current":[48],"methods":[49],"pay":[50],"less":[51],"attention":[52,168],"these":[54,87],"aspects.":[55],"In":[56,89,211],"addition,":[57,212],"existing":[59,259],"feature-fusion":[60],"mechanisms":[61],"frequently":[62],"ignore":[63],"semantic":[64],"inconsistencies":[65],"features":[67,112,203,209],"at":[68],"different":[69],"scales,":[70],"making":[71],"particularly":[73],"challenging.":[74],"Here,":[75],"we":[76,100,119,213],"propose":[77],"global-local":[79,94],"hierarchical":[80],"multiscale":[81],"interaction":[82],"network":[83,196],"(GL-MSIN)":[84],"address":[86],"issues.":[88],"GL-MSIN,":[90],"better":[92],"exploit":[93],"information":[95,152],"images,":[99],"design":[101],"an":[102,215],"EN-Trans":[103,117],"block":[104],"as":[105],"basic":[107],"component":[108],"generate":[110,200],"global&#x2013;local":[111],"about":[113,153],"language.":[114],"Within":[115],"each":[116],"block,":[118],"incorporate":[120],"self-attention":[124],"module":[125,145],"into":[126],"visual":[128,187],"backbone":[129],"capture":[131,148],"details,":[133],"while":[134],"also":[135,235],"designing":[136],"gated":[138],"enhancement":[139,144],"pathway":[140,160],"(GEM)":[146],"inject":[150],"At":[155],"core":[157],"of":[158,181,222,252],"this":[159],"is":[161,197],"GEM,":[163],"which":[164,227],"employs":[165],"lightweight":[167],"mechanism":[169],"expand":[171],"pixel-level":[172],"interactions":[173],"across":[174],"entire":[176],"image,":[177],"enabling":[178],"effective":[179],"context":[183],"from":[184],"locally":[185],"rich":[186],"features.":[188],"Furthermore,":[189],"learnable":[191],"fusion":[192],"feature-based":[193],"iterative":[194],"refinement":[195],"designed":[198],"final":[201],"fused":[202],"overcome":[205],"inconsistency":[206],"issue":[207],"fusion.":[210],"curate":[214],"extensive":[216],"dataset,":[217],"geographic":[218,243],"RefRS":[219],"(GRefRS),":[220],"consisting":[221],"70":[223],"328":[224],"image-expression-mask":[225],"triplets,":[226],"not":[228],"only":[229],"presents":[230],"more":[231,237],"complex":[232],"scenarios":[233],"but":[234],"provides":[236],"practical":[238],"expressions":[241],"attributes.":[244],"Our":[245],"experimental":[246],"evaluations":[247],"demonstrate":[248],"exceptional":[250],"performance":[251],"GL-MSIN":[253],"GRefRS":[256],"mainstream":[260],"datasets.":[261]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-21T00:00:00"}
