{"id":"https://openalex.org/W4411630203","doi":"https://doi.org/10.18653/v1/2024.eacl-long.98","title":"VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection","display_name":"VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630203","doi":"https://doi.org/10.18653/v1/2024.eacl-long.98"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.98","pdf_url":"https://aclanthology.org/2024.eacl-long.98.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-long.98.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037312803","display_name":"Arushi Rai","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arushi Rai","raw_affiliation_strings":["University of Pittsburgh University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072882318","display_name":"Adriana Kovashka","orcid":"https://orcid.org/0000-0003-1901-9660"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adriana Kovashka","raw_affiliation_strings":["University of Pittsburgh University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27989385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1632","last_page":"1649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9962000250816345,"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":0.991599977016449,"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/vetting","display_name":"Vetting","score":0.9689978361129761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.701839804649353},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6658004522323608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6561118960380554},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5991223454475403},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5694124102592468},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5406605005264282},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4960800111293793},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12857457995414734}],"concepts":[{"id":"https://openalex.org/C2777230681","wikidata":"https://www.wikidata.org/wiki/Q7923820","display_name":"Vetting","level":2,"score":0.9689978361129761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.701839804649353},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6658004522323608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6561118960380554},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5991223454475403},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5694124102592468},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5406605005264282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4960800111293793},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12857457995414734}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.98","pdf_url":"https://aclanthology.org/2024.eacl-long.98.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-long.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.98","pdf_url":"https://aclanthology.org/2024.eacl-long.98.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G5997888051","display_name":"CAREER: Natural Narratives and Multimodal Context as Weak Supervision for Learning Object Categories","funder_award_id":"2046853","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7928472606","display_name":"RI: Small: Domain-robust object detection through shape and context","funder_award_id":"2006885","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310174","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630203.pdf","grobid_xml":"https://content.openalex.org/works/W4411630203.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3137893487","https://openalex.org/W2588786532","https://openalex.org/W2169930420","https://openalex.org/W2108865840","https://openalex.org/W2802914690","https://openalex.org/W4248793399","https://openalex.org/W3120410482","https://openalex.org/W2980021769","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"The":[0],"use":[1,63],"of":[2,16,79],"large-scale":[3,26],"vision-language":[4],"datasets":[5,27],"is":[6,41,100],"limited":[7],"for":[8,31,38,47,65],"object":[9,67],"detection":[10,68],"due":[11],"to":[12,55,119,138],"the":[13,77,104,117],"negative":[14],"impact":[15],"label":[17,80,99,133],"noise":[18,81],"on":[19,122,143],"localization.Prior":[20],"methods":[21],"have":[22],"shown":[23],"how":[24],"such":[25],"can":[28,34,129],"be":[29],"used":[30],"pretraining,":[32],"which":[33],"provide":[35],"initial":[36],"signal":[37],"localization,":[39],"but":[40],"insufficient":[42],"without":[43,70,132],"clean":[44],"bounding-box":[45],"data":[46],"at":[48],"least":[49],"some":[50],"categories.We":[51,115],"propose":[52],"a":[53,92],"technique":[54],"\"vet\"":[56],"labels":[57],"extracted":[58,98],"from":[59],"noisy":[60],"captions,":[61],"and":[62,75,90,113,125],"them":[64],"weakly-supervised":[66],"(WSOD),":[69],"any":[71],"bounding":[72],"boxes.We":[73],"analyze":[74],"annotate":[76],"types":[78],"in":[82,84,103],"captions":[83],"our":[85],"Caption":[86],"Label":[87],"Noise":[88],"dataset,":[89],"train":[91],"classifier":[93,108,118],"that":[94,127],"predicts":[95],"if":[96],"an":[97],"actually":[101],"present":[102],"image":[105],"or":[106],"not.Our":[107],"generalizes":[109],"across":[110,114],"dataset":[111],"boundaries":[112],"compare":[116],"nine":[120],"baselines":[121],"five":[123],"datasets,":[124],"demonstrate":[126],"it":[128],"improve":[130],"WSOD":[131],"vetting":[134],"by":[135],"30%":[136],"(31.2":[137],"40.5":[139],"mAP":[140],"when":[141],"evaluated":[142],"PASCAL":[144],"VOC).":[145]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}