{"id":"https://openalex.org/W7160317905","doi":"https://doi.org/10.1109/wacv61042.2026.00041","title":"OW-Rep: Open World Object Detection with Instance Representation Learning","display_name":"OW-Rep: Open World Object Detection with Instance Representation Learning","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160317905","doi":"https://doi.org/10.1109/wacv61042.2026.00041"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00041","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":["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/A5135370771","display_name":"Sunoh Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Sunoh Lee","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064213466","display_name":"Minsik Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minsik Jeon","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102946685","display_name":"Jihong Min","orcid":"https://orcid.org/0000-0003-4231-0915"},"institutions":[{"id":"https://openalex.org/I2801036362","display_name":"Agency for Defense Development","ror":"https://ror.org/05fhe0r85","country_code":"KR","type":"government","lineage":["https://openalex.org/I1327899338","https://openalex.org/I1344042128","https://openalex.org/I2801036362","https://openalex.org/I2801339556"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihong Min","raw_affiliation_strings":["Agency for Defense Development"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Defense Development","institution_ids":["https://openalex.org/I2801036362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135350461","display_name":"Junwon Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junwon Seo","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52441902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"339","last_page":"349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5299999713897705,"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":0.5299999713897705,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11299999803304672,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.07450000196695328,"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":0.5554999709129333},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44920000433921814},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.4156999886035919},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41519999504089355},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.4016999900341034},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3580000102519989},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.35440000891685486}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6570000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384000182151794},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5554999709129333},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44920000433921814},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.4156999886035919},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4146000146865845},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.4016999900341034},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.3361999988555908},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00041","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.40821778774261475,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2603203130","https://openalex.org/W2887783173","https://openalex.org/W2952122856","https://openalex.org/W2962766617","https://openalex.org/W3009436130","https://openalex.org/W3035524453","https://openalex.org/W3157926441","https://openalex.org/W3159481202","https://openalex.org/W3165926952","https://openalex.org/W3174803757","https://openalex.org/W3176709420","https://openalex.org/W3194038966","https://openalex.org/W3217535672","https://openalex.org/W4223646441","https://openalex.org/W4310557340","https://openalex.org/W4312547276","https://openalex.org/W4312956471","https://openalex.org/W4313018996","https://openalex.org/W4313026212","https://openalex.org/W4386065367","https://openalex.org/W4386066015","https://openalex.org/W4386071855","https://openalex.org/W4386075732","https://openalex.org/W4386076022","https://openalex.org/W4386076029","https://openalex.org/W4390872587","https://openalex.org/W4390872835","https://openalex.org/W4390872928","https://openalex.org/W4390874575","https://openalex.org/W4393158977","https://openalex.org/W4401375179","https://openalex.org/W4401415576","https://openalex.org/W4402716047","https://openalex.org/W4402727796","https://openalex.org/W4402727951","https://openalex.org/W4402753798","https://openalex.org/W4404545825","https://openalex.org/W4404612908","https://openalex.org/W4409367135","https://openalex.org/W7133199607","https://openalex.org/W7133231839"],"related_works":[],"abstract_inverted_index":{"Open":[0],"World":[1],"Object":[2],"Detection":[3],"(OWOD)":[4],"addresses":[5],"realistic":[6],"scenarios":[7],"where":[8],"unseen":[9],"object":[10,121,185],"classes":[11,18],"emerge,":[12],"enabling":[13,87,163],"detectors":[14],"trained":[15],"on":[16,36],"known":[17],"to":[19,76,90,137,154,166],"detect":[20,78],"unknown":[21,38,79,140,184],"objects":[22,80],"and":[23,56,64,81,107,115,171,187],"incrementally":[24],"incorporate":[25],"the":[26,43,73,88,105,124,133,155,164],"knowledge":[27,109],"they":[28,40],"provide.":[29],"While":[30],"existing":[31],"OWOD":[32,74],"methods":[33],"primarily":[34],"focus":[35],"detecting":[37],"objects,":[39,49],"often":[41],"overlook":[42],"rich":[44,84,106],"semantic":[45,93,130,149],"relationships":[46,94],"between":[47,95],"detected":[48],"which":[50],"are":[51],"essential":[52],"for":[53],"scene":[54],"understanding":[55],"applications":[57],"in":[58,195],"open-world":[59,62,120,200],"environments":[60],"(e.g.,":[61],"tracking":[63],"novel":[65],"class":[66],"discovery).":[67],"In":[68],"this":[69,98],"paper,":[70],"we":[71,100],"extend":[72],"framework":[75],"jointly":[77],"learn":[82,167],"semantically":[83,169],"instance":[85,173,188],"embeddings,":[86],"detector":[89,165],"capture":[91],"fine-grained":[92],"instances.":[96],"To":[97],"end,":[99],"propose":[101],"modules":[102],"that":[103,178],"leverage":[104],"generalizable":[108,172],"of":[110],"Vision":[111],"Foundation":[112],"Models":[113],"(VFMs)":[114],"can":[116],"be":[117],"integrated":[118],"into":[119],"detectors.":[122],"First,":[123],"Unknown":[125],"Box":[126],"Refine":[127],"Module":[128,145],"uses":[129],"masks":[131],"from":[132,151],"Segment":[134],"Anything":[135],"Model":[136],"accurately":[138],"localize":[139],"objects.":[141],"The":[142],"Embedding":[143],"Transfer":[144],"then":[146],"distills":[147],"instance-wise":[148],"similarities":[150],"VFM":[152],"features":[153],"detector\u2019s":[156],"embeddings":[157],"via":[158],"a":[159,168],"relaxed":[160],"contrastive":[161],"loss,":[162],"meaningful":[170],"feature.":[174],"Extensive":[175],"experiments":[176],"show":[177],"our":[179],"method":[180],"significantly":[181],"improves":[182],"both":[183],"detection":[186],"embedding":[189],"quality,":[190],"while":[191],"also":[192],"enhancing":[193],"performance":[194],"downstream":[196],"tasks":[197],"such":[198],"as":[199],"tracking.":[201]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}