{"id":"https://openalex.org/W7138194579","doi":"https://doi.org/10.1609/aaai.v40i7.37490","title":"Improving Target Presence and Plurality Recognition for Generalized Referring Image Segmentation","display_name":"Improving Target Presence and Plurality Recognition for Generalized Referring Image Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138194579","doi":"https://doi.org/10.1609/aaai.v40i7.37490"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i7.37490","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37490","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i7.37490","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074668738","display_name":"Namyup Kim","orcid":"https://orcid.org/0000-0002-5503-2857"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namyup Kim","raw_affiliation_strings":["Pohang University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661525","display_name":"Jinsung Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinsung Lee","raw_affiliation_strings":["Pohang University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101352002","display_name":"Suha Kwak","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suha Kwak","raw_affiliation_strings":["Pohang University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5700","last_page":"5708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9010000228881836,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9010000228881836,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.018300000578165054,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.5884000062942505},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5361999869346619},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.525600016117096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41269999742507935},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3813999891281128},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.34040001034736633},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3312000036239624},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6730999946594238},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5361999869346619},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5072000026702881},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.25769999623298645},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i7.37490","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37490","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37490","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37490","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37490","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6342687606811523}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generalized":[0],"referring":[1],"image":[2,11],"segmentation":[3],"(RIS)":[4],"aims":[5],"to":[6,40,99,118,149],"segment":[7],"regions":[8],"in":[9,85],"an":[10,94],"described":[12],"by":[13],"a":[14,36,47,114,140],"natural":[15],"language":[16],"expression,":[17],"handling":[18],"not":[19],"only":[20],"single-target":[21],"but":[22],"also":[23],"no-":[24],"and":[25,55,81,102,108,123],"multi-target":[26,60,103],"scenarios.":[27,88],"Previous":[28],"approaches":[29],"have":[30],"proposed":[31],"new":[32],"components":[33,80],"that":[34,65,145],"enable":[35],"conventional":[37,72],"RIS":[38,73],"model":[39],"handle":[41,100],"these":[42,66],"additional":[43,79],"scenarios,":[44,104],"such":[45,86],"as":[46],"target":[48,121],"presence":[49,122],"prediction":[50],"head":[51],"for":[52,59],"no-target":[53,101],"scenarios":[54],"multiple":[56],"mask":[57],"candidates":[58],"cases.":[61],"However,":[62],"we":[63,92,137],"observe":[64],"methods":[67,132],"predominantly":[68],"rely":[69],"on":[70],"the":[71,78],"backbone":[74],"without":[75],"fully":[76],"integrating":[77],"thus":[82],"still":[83],"struggle":[84],"general":[87],"To":[89],"address":[90],"this,":[91],"propose":[93],"effective":[95],"framework":[96,148],"specifically":[97],"tailored":[98],"incorporating":[105],"both":[106,120],"architectural":[107],"data-driven":[109],"approaches.":[110,154],"Our":[111],"architecture":[112],"employs":[113],"learnable":[115],"query":[116],"designed":[117],"understand":[119],"plurality.":[124],"While":[125],"this":[126],"approach":[127],"alone":[128],"outperforms":[129],"previous":[130],"state-of-the-art":[131],"with":[133],"similar":[134],"computational":[135],"requirements,":[136],"further":[138],"introduce":[139],"novel":[141],"data":[142],"augmentation":[143],"strategy":[144],"enables":[146],"our":[147],"surpass":[150],"computationally":[151],"intensive":[152],"LMM-based":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}