{"id":"https://openalex.org/W4387421670","doi":"https://doi.org/10.1145/3577190.3614176","title":"AIUnet: Asymptotic inference with U2-Net for referring image segmentation","display_name":"AIUnet: Asymptotic inference with U2-Net for referring image segmentation","publication_year":2023,"publication_date":"2023-10-07","ids":{"openalex":"https://openalex.org/W4387421670","doi":"https://doi.org/10.1145/3577190.3614176"},"language":"en","primary_location":{"id":"doi:10.1145/3577190.3614176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614176","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-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/A5001473818","display_name":"Jiangquan Li","orcid":"https://orcid.org/0000-0003-4809-1864"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiangquan Li","raw_affiliation_strings":["SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China"],"raw_orcid":"https://orcid.org/0000-0003-4809-1864","affiliations":[{"raw_affiliation_string":"SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102864042","display_name":"Shimin Shan","orcid":"https://orcid.org/0000-0003-0864-7258"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Shan","raw_affiliation_strings":["SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China"],"raw_orcid":"https://orcid.org/0000-0003-0864-7258","affiliations":[{"raw_affiliation_string":"SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002476102","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0001-8013-4372"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China"],"raw_orcid":"https://orcid.org/0000-0001-8013-4372","affiliations":[{"raw_affiliation_string":"SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060622132","display_name":"Kaiping Xu","orcid":"https://orcid.org/0000-0001-7388-7878"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiping Xu","raw_affiliation_strings":["SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China"],"raw_orcid":"https://orcid.org/0000-0001-7388-7878","affiliations":[{"raw_affiliation_string":"SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101735201","display_name":"Xiwen Hu","orcid":"https://orcid.org/0009-0000-4053-5438"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiwen Hu","raw_affiliation_strings":["SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China"],"raw_orcid":"https://orcid.org/0009-0000-4053-5438","affiliations":[{"raw_affiliation_string":"SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004832199","display_name":"Mingcheng Xue","orcid":"https://orcid.org/0000-0002-6614-8871"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingcheng Xue","raw_affiliation_strings":["SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China"],"raw_orcid":"https://orcid.org/0000-0002-6614-8871","affiliations":[{"raw_affiliation_string":"SCHOOL OF SOFTWARE TECHNOLOGY, DALIAN UNIVERSITY OF TECHNOLOGY, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001473818"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13506711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.844398021697998},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7357689738273621},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6263152360916138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.619970440864563},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6014383435249329},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5444115996360779},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5136746764183044},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.48907023668289185},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.47705191373825073},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.45306476950645447},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.432841420173645},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41858527064323425},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3963259756565094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38232994079589844},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07672062516212463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.844398021697998},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7357689738273621},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6263152360916138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.619970440864563},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6014383435249329},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5444115996360779},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5136746764183044},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.48907023668289185},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.47705191373825073},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.45306476950645447},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.432841420173645},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41858527064323425},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3963259756565094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38232994079589844},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07672062516212463},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577190.3614176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614176","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2605127024","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2894964039","https://openalex.org/W2907750714","https://openalex.org/W2963109634","https://openalex.org/W2964345792","https://openalex.org/W2980088508","https://openalex.org/W3003423830","https://openalex.org/W3004019157","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3035097537","https://openalex.org/W3081752372","https://openalex.org/W3093025045","https://openalex.org/W3099166112","https://openalex.org/W3108748824","https://openalex.org/W3135367836","https://openalex.org/W3169998662","https://openalex.org/W3172522282","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3206209177","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4312543911","https://openalex.org/W4312690830"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W4321636575","https://openalex.org/W613940353","https://openalex.org/W1986418932","https://openalex.org/W2381031055","https://openalex.org/W2366070815"],"abstract_inverted_index":{"Referring":[0],"image":[1,11],"segmentation":[2],"aims":[3],"to":[4,111,122,133],"segment":[5],"a":[6,14,61,68,105,129],"target":[7],"object":[8],"from":[9],"an":[10,49],"by":[12],"providing":[13],"natural":[15],"language":[16],"expression.":[17],"While":[18],"recent":[19],"methods":[20],"have":[21,26],"made":[22],"remarkable":[23],"advancements,":[24],"few":[25],"designed":[27],"effective":[28],"deep":[29],"fusion":[30],"processes":[31],"for":[32],"cross-model":[33,80,120],"features":[34,93,121],"or":[35],"focused":[36],"on":[37,88,145],"the":[38,113],"fine":[39,116],"details":[40,117],"of":[41,58,79,115],"vision.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,103],"propose":[47,104],"AIUnet,":[48],"asymptotic":[50],"inference":[51],"method":[52],"that":[53,140],"uses":[54],"U2-Net.":[55],"The":[56,125],"core":[57],"AIUnet":[59,141],"is":[60,149],"Cross-model":[62],"U2-Net":[63],"(CMU)":[64],"module,":[65],"which":[66],"integrates":[67],"Text":[69],"guide":[70],"vision":[71],"(TGV)":[72],"module":[73,110,127],"into":[74],"U2-Net,":[75],"achieving":[76],"efficient":[77],"interaction":[78],"information":[81,90,98],"at":[82,151],"different":[83],"scales.":[84],"CMU":[85],"focuses":[86],"more":[87],"location":[89],"in":[91,99],"high-level":[92],"and":[94,118],"learns":[95],"finer":[96],"detail":[97],"low-level":[100],"features.":[101,136],"Additionally,":[102],"Features":[106],"Enhance":[107],"Decoder":[108],"(FED)":[109],"improve":[112],"recognition":[114],"decode":[119],"binary":[123],"masks.":[124],"FED":[126],"leverages":[128],"simple":[130],"CNN-based":[131],"approach":[132],"enhance":[134],"multi-modal":[135],"Our":[137],"experiments":[138],"show":[139],"achieved":[142],"competitive":[143],"results":[144],"three":[146],"standard":[147],"datasets.Code":[148],"available":[150],"https://github.com/LJQbiu/AIUnet.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}