{"id":"https://openalex.org/W4412081928","doi":"https://doi.org/10.1109/tgrs.2025.3586620","title":"PMTSeg: Prompt-Driven Multimodal Transformer for Task-Adapted Remote Sensing Image Segmentation","display_name":"PMTSeg: Prompt-Driven Multimodal Transformer for Task-Adapted Remote Sensing Image Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412081928","doi":"https://doi.org/10.1109/tgrs.2025.3586620"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3586620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3586620","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":["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/A5114500391","display_name":"Kejun Liu","orcid":"https://orcid.org/0009-0008-2332-6157"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejun Liu","raw_affiliation_strings":["School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0008-2332-6157","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076599921","display_name":"Xuesong Yan","orcid":"https://orcid.org/0000-0003-0008-3873"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Yan","raw_affiliation_strings":["School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0008-3873","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753233","display_name":"Yuanyuan Liu","orcid":"https://orcid.org/0000-0003-0465-3976"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Liu","raw_affiliation_strings":["School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0465-3976","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033240507","display_name":"Chang Tang","orcid":"https://orcid.org/0000-0002-6515-7696"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Tang","raw_affiliation_strings":["School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-6515-7696","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy (JD.com), Beijing, China","JD Explore Academy,JD.com, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy (JD.com), Beijing, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD Explore Academy,JD.com, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718116","display_name":"Wei Luo","orcid":"https://orcid.org/0000-0003-1431-4134"},"institutions":[{"id":"https://openalex.org/I4210129465","display_name":"Wuhan Ship Development & Design Institute","ror":"https://ror.org/02mcdae06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129465"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Luo","raw_affiliation_strings":["Department of Innovation Center, China Ship Development and Design Center, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Innovation Center, China Ship Development and Design Center, Wuhan, China","institution_ids":["https://openalex.org/I4210129465"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076872319","display_name":"Wujie Zhou","orcid":"https://orcid.org/0000-0002-3055-2493"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wujie Zhou","raw_affiliation_strings":["School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China","University of Science and Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3055-2493","affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"University of Science and Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385579","display_name":"Hongyan Zhang","orcid":"https://orcid.org/0000-0002-7894-5755"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan Zhang","raw_affiliation_strings":["School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-7894-5755","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20036327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.8695999979972839,"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"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.8695999979972839,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8467000126838684,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8414000272750854,"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":0.7011985778808594},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6041384935379028},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6002910733222961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5489434003829956},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5417999625205994},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5281548500061035},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4818876385688782},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.16977781057357788},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11168777942657471},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0727185308933258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011985778808594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6041384935379028},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6002910733222961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489434003829956},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5417999625205994},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5281548500061035},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4818876385688782},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.16977781057357788},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11168777942657471},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0727185308933258},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3586620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3586620","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1034316256","display_name":null,"funder_award_id":"2023AFB572","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"},{"id":"https://openalex.org/G4271941372","display_name":null,"funder_award_id":"62076227","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G995208696","display_name":null,"funder_award_id":"KLIGIP- 2022-B10","funder_id":"https://openalex.org/F4320328373","funder_display_name":"National Key Laboratory 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/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null},{"id":"https://openalex.org/F4320328373","display_name":"National Key Laboratory Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1526448290","https://openalex.org/W1973965874","https://openalex.org/W2395611524","https://openalex.org/W2560023338","https://openalex.org/W2963150697","https://openalex.org/W2963995737","https://openalex.org/W3035942737","https://openalex.org/W3046981947","https://openalex.org/W3090912710","https://openalex.org/W3106808132","https://openalex.org/W3185151088","https://openalex.org/W3206254920","https://openalex.org/W3211612835","https://openalex.org/W4214613769","https://openalex.org/W4220917101","https://openalex.org/W4225487034","https://openalex.org/W4226530543","https://openalex.org/W4292830135","https://openalex.org/W4298326888","https://openalex.org/W4300928835","https://openalex.org/W4312272867","https://openalex.org/W4312460151","https://openalex.org/W4312815172","https://openalex.org/W4315606133","https://openalex.org/W4327785494","https://openalex.org/W4366377620","https://openalex.org/W4384938791","https://openalex.org/W4385245566","https://openalex.org/W4386071839","https://openalex.org/W4386075633","https://openalex.org/W4386076491","https://openalex.org/W4386189887","https://openalex.org/W4386362924","https://openalex.org/W4390871550","https://openalex.org/W4392543906","https://openalex.org/W4393131857","https://openalex.org/W4401069815","https://openalex.org/W4402557624","https://openalex.org/W4402702940","https://openalex.org/W4402754258","https://openalex.org/W4402916290","https://openalex.org/W4403791238","https://openalex.org/W4403843568","https://openalex.org/W4406904711","https://openalex.org/W4408145566"],"related_works":["https://openalex.org/W2121524756","https://openalex.org/W782553550","https://openalex.org/W4379231730","https://openalex.org/W1987967678","https://openalex.org/W4389858081","https://openalex.org/W2633218168","https://openalex.org/W4235897794","https://openalex.org/W2059707233","https://openalex.org/W1983126463","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Multimodal":[0,101,113],"remote":[1,10],"sensing":[2,11],"image":[3,12],"segmentation":[4,90,219],"(MRSIS)":[5],"is":[6],"important":[7],"for":[8,103,194],"intelligent":[9],"(RS)":[13],"interpretation,":[14],"which":[15],"encompasses":[16],"three":[17,108,203,218],"distinct":[18],"tasks:":[19],"semantic":[20,70,149],"segmentation,":[21,23],"instance":[22],"and":[24,38,72,78,123,147,182,196,208,224],"panoptic":[25],"segmentation.":[26],"Existing":[27],"methods":[28,215],"typically":[29],"address":[30,172],"individual":[31],"tasks":[32],"with":[33],"specialized":[34],"models,":[35],"limiting":[36],"generalization":[37],"real-world":[39],"applicability.":[40],"Multi-task":[41],"learning":[42,88],"approaches":[43],"have":[44],"introduced":[45],"separated":[46],"task":[47,81,174],"heads":[48],"to":[49,62,84,164,171,186,227],"unify":[50],"tasks,":[51,190,220],"yet":[52],"we":[53,96],"identify":[54],"two":[55],"key":[56,109],"challenges":[57],"when":[58],"directly":[59],"applying":[60],"them":[61],"MRSIS:":[63],"(1)":[64,111],"the":[65,80,134,158,173,176],"modality":[66,135],"gap,":[67,82,175],"arising":[68],"from":[69],"discrepancies":[71,74],"granularity":[73],"across":[75,145,189],"RS":[76],"modalities,":[77],"(2)":[79,117],"due":[83],"varying":[85],"preferences":[86],"in":[87,216],"different":[89],"tasks.":[91],"To":[92],"overcome":[93],"these":[94,155],"challenges,":[95],"propose":[97],"PMTSeg\u2014a":[98],"novel":[99],"Prompt-driven":[100,127],"Transformer":[102],"task-adapted":[104,179,183],"MRSIS.":[105,228],"PMTSeg":[106,211],"integrates":[107,154],"components:":[110],"Task-common":[112,118],"Affinity":[114],"Approximation":[115],"(TMAA),":[116],"Multi-scale":[119],"Semantic":[120],"Fusion":[121],"(TMSF),":[122],"(3)":[124],"a":[125,222],"unified":[126,223],"Segmentation":[128],"Head":[129],"(PSH).":[130],"First,":[131],"TMAA":[132],"addresses":[133],"gap":[136],"by":[137],"approximating":[138],"inter-modal":[139],"affinity":[140],"matrices,":[141],"extracting":[142],"task-common":[143,168],"features":[144,156],"modalities":[146],"aligning":[148],"information.":[150],"Then,":[151],"TMSF":[152],"further":[153],"using":[157],"scale-matched":[159],"fusion":[160],"at":[161],"multiple":[162],"scales":[163],"produce":[165],"enriched,":[166],"multi-scale":[167],"features.":[169],"Moreover,":[170],"PSH":[177],"leverages":[178],"text":[180],"prompts":[181],"contrastive":[184],"loss":[185],"model":[187],"relationships":[188],"enabling":[191],"adaptive":[192],"optimization":[193],"robust":[195],"universal":[197],"MRSIS":[198,204],"performance.":[199],"Extensive":[200],"experiments":[201],"on":[202],"datasets\u2014VALID,":[205],"SEMCITY":[206],"TOULOUSE,":[207],"UBCV2\u2014demonstrate":[209],"that":[210],"significantly":[212],"surpasses":[213],"state-of-the-art":[214],"all":[217],"offering":[221],"accurate":[225],"solution":[226]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}