{"id":"https://openalex.org/W4416054676","doi":"https://doi.org/10.1109/wacv61042.2026.00589","title":"MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation","display_name":"MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416054676","doi":"https://doi.org/10.1109/wacv61042.2026.00589"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/2510.17866","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101506137","display_name":"Sungmin Cho","orcid":"https://orcid.org/0000-0003-2308-7906"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungmin Cho","raw_affiliation_strings":["Netmarble"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netmarble","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029966859","display_name":"Sungbum Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungbum Park","raw_affiliation_strings":["Netmarble"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netmarble","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048714368","display_name":"Insoo Oh","orcid":"https://orcid.org/0000-0002-3938-4932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Insoo Oh","raw_affiliation_strings":["Netmarble"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netmarble","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"6090","last_page":"6100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9107999801635742,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9107999801635742,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.014800000004470348,"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"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.010499999858438969,"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/object-detection","display_name":"Object detection","score":0.6658999919891357},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6419000029563904},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6366999745368958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6158000230789185},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5925999879837036},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5719000101089478},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5184999704360962},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5016999840736389}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7677000164985657},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6658999919891357},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6419000029563904},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6366999745368958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212999820709229},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5925999879837036},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.3801000118255615},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2720000147819519},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.17866","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17866","pdf_url":"https://arxiv.org/pdf/2510.17866","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.2510.17866","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.17866","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.17866","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17866","pdf_url":"https://arxiv.org/pdf/2510.17866","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,41,70],"this":[1],"work,":[2],"we":[3,45,90,125],"present":[4],"MUSE":[5,22,100,128],"(Model-based":[6],"Uncertainty-aware":[7],"Similarity":[8],"Estimation),":[9],"a":[10,47,74,86,130],"training-free":[11],"framework":[12,132],"for":[13,133],"model-based":[14],"zero-shot":[15,134],"2D":[16,24,32,135],"object":[17,33,98,136],"detection":[18,137],"and":[19,31,55,85,116,138],"segmentation.":[20,139],"First,":[21],"incorporates":[23],"multi-view":[25],"templates":[26],"from":[27,35],"3D":[28],"unseen":[29],"objects":[30],"proposals":[34],"the":[36,42,59,65,71,92,105,112],"input":[37],"query":[38],"image,":[39],"respectively.":[40],"embedding":[43,50],"stage,":[44,73],"propose":[46],"new":[48],"feature":[49],"scheme":[51],"which":[52,80],"integrates":[53,81],"class":[54],"patch":[56,60],"embeddings.":[57],"Specifically,":[58],"embeddings":[61],"are":[62],"normalized":[63],"using":[64,95],"generalized":[66],"mean":[67],"pooling":[68],"(GeM).":[69],"matching":[72],"joint":[75],"similarity":[76,93],"score":[77,84,94],"is":[78,129],"introduced,":[79],"an":[82,96],"absolute":[83],"relative":[87],"score.":[88],"Finally,":[89],"update":[91],"uncertainty-aware":[97],"prior.":[99],"achieves":[101],"state-of-the-art":[102],"performance":[103],"on":[104],"BOP":[106],"Challenge":[107],"2025,":[108],"ranking":[109],"first":[110],"in":[111],"Classic":[113],"Core,":[114],"H3,":[115],"Industrial":[117],"tracks\u2014without":[118],"any":[119],"additional":[120],"training":[121],"or":[122],"fine-tuning.":[123],"Therefore,":[124],"believe":[126],"that":[127],"promising":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}