{"id":"https://openalex.org/W7160326410","doi":"https://doi.org/10.1109/wacv61042.2026.00174","title":"Enhancing Object Detection Training via Joint Image-Annotation Generation","display_name":"Enhancing Object Detection Training via Joint Image-Annotation Generation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160326410","doi":"https://doi.org/10.1109/wacv61042.2026.00174"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00174","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/A5075115512","display_name":"Roy Uziel","orcid":null},"institutions":[{"id":"https://openalex.org/I118136607","display_name":"General Motors (United States)","ror":"https://ror.org/05addee68","country_code":"US","type":"company","lineage":["https://openalex.org/I118136607"]},{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]},{"id":"https://openalex.org/I4210135317","display_name":"General Motors (Poland)","ror":"https://ror.org/03n3nz506","country_code":"PL","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I4210135317"]}],"countries":["IN","PL","US"],"is_corresponding":false,"raw_author_name":"Roy Uziel","raw_affiliation_strings":["Technical Center Israel,General Motors"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical Center Israel,General Motors","institution_ids":["https://openalex.org/I118136607","https://openalex.org/I2801120862","https://openalex.org/I4210135317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076874228","display_name":"Oded Bialer","orcid":"https://orcid.org/0000-0001-8521-3416"},"institutions":[{"id":"https://openalex.org/I118136607","display_name":"General Motors (United States)","ror":"https://ror.org/05addee68","country_code":"US","type":"company","lineage":["https://openalex.org/I118136607"]},{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]},{"id":"https://openalex.org/I4210135317","display_name":"General Motors (Poland)","ror":"https://ror.org/03n3nz506","country_code":"PL","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I4210135317"]}],"countries":["IN","PL","US"],"is_corresponding":false,"raw_author_name":"Oded Bialer","raw_affiliation_strings":["Technical Center Israel,General Motors"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical Center Israel,General Motors","institution_ids":["https://openalex.org/I118136607","https://openalex.org/I2801120862","https://openalex.org/I4210135317"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"1736","last_page":"1745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.19820000231266022,"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":0.19820000231266022,"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":0.1843000054359436,"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":0.08370000123977661,"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/joint","display_name":"Joint (building)","score":0.6092000007629395},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5778999924659729},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5577999949455261},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45410001277923584},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3407000005245209},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31220000982284546}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6075999736785889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6014999747276306},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5918999910354614},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5577999949455261},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.27900001406669617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00174","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2183341477","https://openalex.org/W2962785568","https://openalex.org/W3035574168","https://openalex.org/W4312933868","https://openalex.org/W4385801729","https://openalex.org/W4386065257","https://openalex.org/W4386066731","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4390872387","https://openalex.org/W4390872876","https://openalex.org/W4390873054","https://openalex.org/W4390873211","https://openalex.org/W4390873784","https://openalex.org/W4390874575","https://openalex.org/W4393148714","https://openalex.org/W4394597085","https://openalex.org/W4394625750","https://openalex.org/W4402623742","https://openalex.org/W4402704533","https://openalex.org/W4402716206","https://openalex.org/W4402727668","https://openalex.org/W4402754201","https://openalex.org/W4402916127","https://openalex.org/W4403049104","https://openalex.org/W4412468250","https://openalex.org/W7133185348","https://openalex.org/W7133198434","https://openalex.org/W7155217012"],"related_works":[],"abstract_inverted_index":{"Incorporating":[0],"generated":[1],"annotated":[2],"data":[3],"into":[4],"training":[5,69],"sets":[6],"can":[7],"improve":[8],"object":[9,72],"detection.":[10],"Prior":[11],"approaches":[12],"either":[13],"condition":[14],"image":[15],"generation":[16],"on":[17],"annotation":[18],"layouts,":[19],"limiting":[20],"diversity":[21],"and":[22,30,45,50,62],"often":[23],"causing":[24],"misalignment,":[25],"or":[26],"generate":[27],"images":[28,44],"independently":[29],"annotate":[31],"them":[32],"afterward,":[33],"reducing":[34],"accuracy.":[35],"We":[36],"introduce":[37],"a":[38],"diffusion":[39],"model":[40],"that":[41],"jointly":[42],"generates":[43],"annotations,":[46],"enabling":[47],"their":[48],"co-evolution":[49],"mutual":[51],"dependency":[52],"throughout":[53],"the":[54,67],"process.":[55],"This":[56],"design":[57],"achieves":[58],"tight":[59],"image-annotation":[60],"alignment":[61],"produces":[63],"diverse":[64],"scenarios":[65],"beyond":[66],"original":[68],"set,":[70],"enhancing":[71],"detection":[73],"performance":[74],"when":[75],"used":[76],"in":[77],"training.":[78]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}