{"id":"https://openalex.org/W7160251786","doi":"https://doi.org/10.1109/wacv61042.2026.00079","title":"Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?","display_name":"Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160251786","doi":"https://doi.org/10.1109/wacv61042.2026.00079"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00079","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/A5011554506","display_name":"Annika M\u00fctze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Annika M\u00fctze","raw_affiliation_strings":["Osnabrück University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osnabrück University,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030433920","display_name":"Sadia Ilyas","orcid":"https://orcid.org/0000-0001-9247-7540"},"institutions":[{"id":"https://openalex.org/I4210130520","display_name":"Aptiv (Germany)","ror":"https://ror.org/039sb8791","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107152","https://openalex.org/I4210130520"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sadia Ilyas","raw_affiliation_strings":["Aptiv Services Deutschland GmbH,Wuppertal,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aptiv Services Deutschland GmbH,Wuppertal,Germany","institution_ids":["https://openalex.org/I4210130520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135393051","display_name":"Chrsitian D\u00f6rpelkus","orcid":null},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chrsitian D\u00f6rpelkus","raw_affiliation_strings":["University of Wuppertal,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wuppertal,Germany","institution_ids":["https://openalex.org/I167360494"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135345643","display_name":"Matthias Rottmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Rottmann","raw_affiliation_strings":["Osnabrück University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osnabrück University,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.50902442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"740","last_page":"750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8025000095367432,"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":0.8025000095367432,"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":0.051899999380111694,"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/T10028","display_name":"Topic Modeling","score":0.025200000032782555,"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/object","display_name":"Object (grammar)","score":0.5102999806404114},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.47189998626708984},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.43790000677108765},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3456000089645386},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3075999915599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6115000247955322},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5648000240325928},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2678999900817871}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00079","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6856489777565002,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329381","display_name":"FRAME","ror":"https://ror.org/014208j94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2081580037","https://openalex.org/W2933610837","https://openalex.org/W2948672349","https://openalex.org/W2963611739","https://openalex.org/W2963944506","https://openalex.org/W2968924835","https://openalex.org/W2983943451","https://openalex.org/W3035574168","https://openalex.org/W3159619744","https://openalex.org/W3177724741","https://openalex.org/W3201301682","https://openalex.org/W4285071854","https://openalex.org/W4285286311","https://openalex.org/W4312497550","https://openalex.org/W4312563428","https://openalex.org/W4312933868","https://openalex.org/W4312956471","https://openalex.org/W4313026212","https://openalex.org/W4385805110","https://openalex.org/W4386083151","https://openalex.org/W4390826350","https://openalex.org/W4390872222","https://openalex.org/W4390873343","https://openalex.org/W4390874554","https://openalex.org/W4394625844","https://openalex.org/W4402716047","https://openalex.org/W4402727832","https://openalex.org/W4403923735","https://openalex.org/W4404612908","https://openalex.org/W4404769985","https://openalex.org/W4410540321","https://openalex.org/W4411528087","https://openalex.org/W7133185348","https://openalex.org/W7133198434","https://openalex.org/W7133227958"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1,83,139,146,177,194,199],"detectors":[2,84,140,178],"such":[3],"as":[4,141,143],"Grounding":[5],"DINO":[6],"are":[7],"trained":[8],"on":[9,17,193,198,214],"vast":[10],"and":[11,126,135,165,210],"diverse":[12],"data,":[13,132],"achieving":[14],"remarkable":[15],"performance":[16],"challenging":[18,160],"datasets.":[19],"Due":[20],"to":[21,27,62,111,206,220],"that,":[22],"it":[23],"is":[24,32,151],"unclear":[25],"where":[26],"find":[28,92,186],"their":[29],"limitations,":[30],"which":[31],"of":[33,53,67,96,181,190],"major":[34],"concern":[35],"when":[36],"using":[37,108],"in":[38,118,179],"safety-critical":[39],"applications.":[40],"Real-world":[41],"data":[42,60,150,216],"does":[43],"not":[44],"provide":[45],"sufficient":[46],"control,":[47],"required":[48],"for":[49],"a":[50,144,159,187,203],"rigorous":[51],"evaluation":[52],"model":[54,68],"generalization.":[55],"In":[56,70],"contrast,":[57],"synthetically":[58,130],"generated":[59,86,131],"allows":[61],"systematically":[63],"explore":[64],"the":[65,129,166],"boundaries":[66],"competence/generalization.":[69],"this":[71],"work,":[72],"we":[73,80,91,103,133,185],"address":[74,100],"two":[75,105,154],"research":[76],"questions:":[77],"1)":[78],"Can":[79,90],"challenge":[81,175,207],"open-vocabulary":[82,138,176,191,208],"with":[85,115],"image":[87],"content?":[88],"2)":[89],"systematic":[93,204],"failure":[94],"modes":[95],"those":[97],"models?":[98],"To":[99],"these":[101,223],"questions,":[102],"design":[104],"automated":[106],"pipelines":[107],"stable":[109],"diffusion":[110],"inpaint":[112],"unusual":[113],"objects":[114],"high":[116],"diversity":[117],"semantics,":[119],"by":[120],"sampling":[121],"multiple":[122,137],"substantives":[123],"from":[124,153],"WordNet":[125],"ChatGPT.":[127],"On":[128],"evaluate":[134],"compare":[136],"well":[142],"classical":[145],"detector.":[147],"The":[148],"synthetic":[149],"derived":[152],"real-world":[155],"datasets,":[156],"namely":[157],"LostAndFound,":[158],"out-of-distribution":[161],"(OOD)":[162],"detection":[163],"benchmark,":[164],"NuImages":[167],"dataset.":[168],"Our":[169],"results":[170],"indicate":[171],"that":[172],"inpainting":[173],"can":[174],"terms":[180],"overlooking":[182],"objects.":[183],"Additionally,":[184],"strong":[188],"dependence":[189],"models":[192,209],"location,":[195],"rather":[196],"than":[197],"semantics.":[200],"This":[201],"provides":[202],"approach":[205],"gives":[211],"valuable":[212],"insights":[213],"how":[215],"could":[217],"be":[218],"acquired":[219],"effectively":[221],"improve":[222],"models.":[224]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}