{"id":"https://openalex.org/W4414359930","doi":"https://doi.org/10.24963/ijcai.2025/213","title":"Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images","display_name":"Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359930","doi":"https://doi.org/10.24963/ijcai.2025/213"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/213","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5101174327","display_name":"Yanguang Sun","orcid":"https://orcid.org/0009-0006-3765-6646"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanguang Sun","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087163038","display_name":"Jiexi Yan","orcid":"https://orcid.org/0000-0002-2544-3057"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiexi Yan","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119558649","display_name":"Jianjun Qian","orcid":"https://orcid.org/0000-0002-5122-267X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjun Qian","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054364063","display_name":"Chunyan Xu","orcid":"https://orcid.org/0000-0002-0814-4362"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyan Xu","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015550399","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-3518-7851"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101672910","display_name":"Lei Luo","orcid":"https://orcid.org/0000-0002-9976-0442"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Luo","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1909","last_page":"1917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9469000101089478,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6671000123023987},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6053000092506409},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3873000144958496},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3675999939441681},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3537999987602234},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016000151634216},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6671000123023987},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6053000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/213","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatically":[0],"segmenting":[1],"objects":[2],"from":[3],"optical":[4],"remote":[5],"sensing":[6],"images":[7],"(ORSIs)":[8],"is":[9,32],"an":[10],"important":[11],"task.":[12],"Most":[13],"existing":[14,64],"models":[15],"are":[16,60],"primarily":[17],"based":[18],"on":[19,156],"either":[20],"convolutional":[21],"or":[22],"Transformer":[23,79],"features,":[24,48],"each":[25],"offering":[26],"distinct":[27],"advantages.":[28],"Exploiting":[29],"both":[30],"advantages":[31],"valuable":[33],"research,":[34],"but":[35],"it":[36],"presents":[37],"several":[38],"challenges,":[39],"including":[40],"the":[41,44,55,65,98,131,149,153],"heterogeneity":[42],"between":[43],"two":[45,107],"types":[46],"of":[47,54],"high":[49],"complexity,":[50],"and":[51,91,109,142],"large":[52],"parameters":[53],"model.":[56],"However,":[57],"these":[58],"issues":[59],"often":[61],"overlooked":[62],"in":[63],"ORSIs":[66],"methods,":[67],"causing":[68],"sub-optimal":[69],"segmentation.":[70],"For":[71],"that,":[72],"we":[73,96,122,135],"propose":[74],"a":[75,82,111,124,137],"novel":[76],"Dual-Perspective":[77],"United":[78],"(DPU-Former)":[80],"with":[81],"unique":[83],"structure":[84],"designed":[85],"to":[86,115,129,140],"simultaneously":[87],"integrate":[88],"long-range":[89],"dependencies":[90],"spatial":[92],"details.":[93],"In":[94],"particular,":[95],"design":[97],"global-local":[99],"mixed":[100],"attention,":[101],"which":[102],"captures":[103],"diverse":[104],"information":[105],"through":[106],"perspectives":[108],"introduces":[110],"Fourier-space":[112],"merging":[113],"strategy":[114],"obviate":[116],"deviations":[117],"for":[118],"efficient":[119],"fusion.":[120],"Furthermore,":[121],"present":[123],"gated":[125],"linear":[126],"feed-forward":[127],"network":[128],"increase":[130],"expressive":[132],"ability.":[133],"Additionally,":[134],"construct":[136],"DPU-Former":[138,150],"decoder":[139],"aggregate":[141],"strength":[143],"features":[144],"at":[145],"different":[146],"layers.":[147],"Consequently,":[148],"model":[151],"outperforms":[152],"state-of-the-art":[154],"methods":[155],"multiple":[157],"datasets.":[158],"Code:":[159],"https://github.com/CSYSI/DPU-Former.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}