{"id":"https://openalex.org/W4417183190","doi":"https://doi.org/10.1109/iccv51701.2025.01854","title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation Through Loopback Synergy","display_name":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation Through Loopback Synergy","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417183190","doi":"https://doi.org/10.1109/iccv51701.2025.01854"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.01738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111929740","display_name":"Ming Dai","orcid":"https://orcid.org/0000-0002-4348-6771"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Dai","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068926305","display_name":"Wenxuan Cheng","orcid":"https://orcid.org/0000-0003-1734-5139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Cheng","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059524537","display_name":"Jiangjiang Liu","orcid":"https://orcid.org/0000-0002-1341-2763"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang-jiang Liu","raw_affiliation_strings":["Baidu VIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu VIS","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100578821","display_name":"Sen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Yang","raw_affiliation_strings":["Baidu VIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu VIS","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006542544","display_name":"Wenxiao Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxiao Cai","raw_affiliation_strings":["Standford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Standford University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101180329","display_name":"Yanpeng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yanpeng Sun","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074121246","display_name":"Wankou Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wankou Yang","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"issue":null,"first_page":"19936","last_page":"19946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.907800018787384,"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":0.907800018787384,"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":0.018799999728798866,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.010099999606609344,"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/segmentation","display_name":"Segmentation","score":0.6887999773025513},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6294000148773193},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6093000173568726},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5224000215530396},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5095000267028809},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3921999931335449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386999726295471},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6887999773025513},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6294000148773193},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5512999892234802},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C2776548248","wikidata":"https://www.wikidata.org/wiki/Q12621536","display_name":"Judgement","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.01738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01738","pdf_url":"https://arxiv.org/pdf/2507.01738","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.01738","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.01738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01738","pdf_url":"https://arxiv.org/pdf/2507.01738","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"Image":[1],"Segmentation":[2],"(RIS)":[3],"is":[4],"a":[5,35,55,72,109,138],"challenging":[6],"task":[7],"that":[8,58,85],"aims":[9],"to":[10,145,152,164],"segment":[11],"objects":[12],"in":[13,42,91,95,156],"an":[14],"image":[15],"based":[16],"on":[17,27],"natural":[18],"language":[19],"expressions.":[20],"While":[21],"prior":[22],"studies":[23],"have":[24],"predominantly":[25],"concentrated":[26],"improving":[28,129],"vision-language":[29],"interactions":[30],"and":[31,66,120,136,167,181],"achieving":[32],"fine-grained":[33],"localization,":[34],"systematic":[36,73],"analysis":[37,74],"of":[38,75,101],"the":[39,76,86,96,115,118,147],"fundamental":[40],"bottlenecks":[41,78],"existing":[43],"RIS":[44,60,80],"frameworks":[45],"remains":[46],"underexplored.":[47],"To":[48,104],"bridge":[49],"this":[50],"gap,":[51],"we":[52,107,134],"propose":[53,108],"DeRIS,":[54],"novel":[56],"framework":[57],"decomposes":[59],"into":[61],"two":[62],"key":[63],"components:":[64],"perception":[65,119],"cognition.":[67],"This":[68],"modular":[69],"decomposition":[70],"facilitates":[71],"primary":[77],"impeding":[79],"performance.":[81],"Our":[82],"findings":[83],"reveal":[84],"predominant":[87],"limitation":[88],"lies":[89],"not":[90],"perceptual":[92],"deficiencies,":[93],"but":[94],"insufficient":[97],"multi-modal":[98],"cognitive":[99],"capacity":[100],"current":[102],"models.":[103],"mitigate":[105],"this,":[106],"Loopback":[110],"Synergy":[111],"mechanism,":[112],"which":[113],"enhances":[114],"synergy":[116],"between":[117],"cognition":[121],"modules,":[122],"thereby":[123],"enabling":[124],"precise":[125],"segmentation":[126],"while":[127],"simultaneously":[128],"robust":[130],"image-text":[131],"comprehension.":[132],"Additionally,":[133],"analyze":[135],"introduce":[137],"simple":[139],"non-referent":[140],"sample":[141],"conversion":[142],"data":[143],"augmentation":[144],"address":[146],"long-tail":[148],"distribution":[149],"issue":[150],"related":[151],"target":[153],"existence":[154],"judgement":[155],"general":[157,177],"scenarios.":[158],"Notably,":[159],"DeRIS":[160],"demonstrates":[161],"inherent":[162],"adaptability":[163],"both":[165],"non-":[166],"multi-referents":[168],"scenarios":[169],"without":[170],"requiring":[171],"specialized":[172],"architectural":[173],"modifications,":[174],"enhancing":[175],"its":[176],"applicability.":[178],"The":[179],"codes":[180],"models":[182],"are":[183],"available":[184],"at":[185],"https://github.com/Dmmm1997/DeRIS.":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}