{"id":"https://openalex.org/W4394597544","doi":"https://doi.org/10.1109/wacv57701.2024.00539","title":"Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection","display_name":"Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4394597544","doi":"https://doi.org/10.1109/wacv57701.2024.00539"},"language":"en","primary_location":{"id":"doi:10.1109/wacv57701.2024.00539","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wacv57701.2024.00539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5013061051","display_name":"Kyle Buettner","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"]},{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Buettner","raw_affiliation_strings":["University of Pittsburgh,Intelligent Systems Program,PA,USA","Intelligent Systems Program, University of Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Intelligent Systems Program,PA,USA","institution_ids":["https://openalex.org/I170201317","https://openalex.org/I4210105785"]},{"raw_affiliation_string":"Intelligent Systems Program, University of Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317","https://openalex.org/I4210105785"]}]},{"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"]},{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adriana Kovashka","raw_affiliation_strings":["University of Pittsburgh,Intelligent Systems Program,PA,USA","Department of Computer Science, University of Pittsburgh, PA, USA","Intelligent Systems Program, University of Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Intelligent Systems Program,PA,USA","institution_ids":["https://openalex.org/I170201317","https://openalex.org/I4210105785"]},{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"Intelligent Systems Program, University of Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317","https://openalex.org/I4210105785"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65422091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5462","last_page":"5472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8754000067710876,"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":0.8754000067710876,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8209999799728394,"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":0.7792999744415283,"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/computer-science","display_name":"Computer science","score":0.7205783724784851},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.602337121963501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5933244228363037},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5229947566986084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4919833838939667},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.462595134973526},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.44796091318130493},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.443695068359375},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3552151024341583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24805963039398193},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07472288608551025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205783724784851},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.602337121963501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5933244228363037},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5229947566986084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4919833838939667},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.462595134973526},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.44796091318130493},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.443695068359375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3552151024341583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24805963039398193},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07472288608551025},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv57701.2024.00539","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wacv57701.2024.00539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":0.5799999833106995,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W2128532956","https://openalex.org/W2138621090","https://openalex.org/W2194775991","https://openalex.org/W2795151422","https://openalex.org/W2963042258","https://openalex.org/W2963936013","https://openalex.org/W2981613027","https://openalex.org/W3014611590","https://openalex.org/W3090114880","https://openalex.org/W3090449556","https://openalex.org/W3098404559","https://openalex.org/W3117585461","https://openalex.org/W3159619744","https://openalex.org/W3172112830","https://openalex.org/W3172141633","https://openalex.org/W3173859428","https://openalex.org/W3182683290","https://openalex.org/W3184735396","https://openalex.org/W3215626407","https://openalex.org/W4225323055","https://openalex.org/W4226464635","https://openalex.org/W4229042118","https://openalex.org/W4282919422","https://openalex.org/W4284961860","https://openalex.org/W4287658071","https://openalex.org/W4287723595","https://openalex.org/W4292794004","https://openalex.org/W4312261477","https://openalex.org/W4312424618","https://openalex.org/W4312539810","https://openalex.org/W4312563428","https://openalex.org/W4312747482","https://openalex.org/W4312890493","https://openalex.org/W4312956471","https://openalex.org/W4386065936","https://openalex.org/W4386071687","https://openalex.org/W4386072101","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4386076683","https://openalex.org/W4390872508","https://openalex.org/W4390872526","https://openalex.org/W6620707391","https://openalex.org/W6639432524","https://openalex.org/W6764990469","https://openalex.org/W6775188310","https://openalex.org/W6780196116","https://openalex.org/W6781630272","https://openalex.org/W6783961830","https://openalex.org/W6783983736","https://openalex.org/W6783990618","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6800139874","https://openalex.org/W6802517928","https://openalex.org/W6803872405","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6811072154","https://openalex.org/W6839745749","https://openalex.org/W6845354634","https://openalex.org/W6849976536"],"related_works":["https://openalex.org/W2114275278","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W1489511283","https://openalex.org/W4387272257","https://openalex.org/W2769899322","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W949345935"],"abstract_inverted_index":{"Vision-language":[0],"alignment":[1,143],"learned":[2],"from":[3,172],"image-caption":[4],"pairs":[5],"has":[6],"been":[7],"shown":[8],"to":[9,90,169],"benefit":[10],"tasks":[11,63],"like":[12],"object":[13,26,44,67,101,124],"recognition":[14],"and":[15,66,93,107,129,154],"detection.":[16],"Methods":[17],"are":[18,29],"mostly":[19],"evaluated":[20],"in":[21,54,82,120,152],"terms":[22],"of":[23,77,80,95,117],"how":[24,49],"well":[25,57],"class":[27],"names":[28],"learned,":[30],"but":[31],"captions":[32],"also":[33],"contain":[34],"rich":[35],"attribute":[36,65,96,118,136,146],"context":[37,53,119,137],"that":[38,135,166],"should":[39],"be":[40,139],"considered":[41,151],"when":[42,62,141],"learning":[43,142],"alignment.":[45],"It":[46],"is":[47,148,161,174],"unclear":[48],"methods":[50],"use":[51],"this":[52,71],"learning,":[55],"as":[56,58],"whether":[59],"models":[60],"succeed":[61],"require":[64],"understanding.":[68],"To":[69],"address":[70],"gap,":[72],"we":[73,167],"conduct":[74],"extensive":[75],"analysis":[76],"the":[78,91,115],"role":[79],"attributes":[81,160,173],"vision-language":[83],"models.":[84],"We":[85,112],"specifically":[86],"measure":[87],"model":[88],"sensitivity":[89],"presence":[92],"meaning":[94,147],"context,":[97],"gauging":[98],"influence":[99],"on":[100],"embeddings":[102],"through":[103],"unsupervised":[104],"phrase":[105],"grounding":[106],"classification":[108],"via":[109],"description":[110],"methods.":[111],"further":[113],"evaluate":[114],"utility":[116],"training":[121,176],"for":[122,144],"open-vocabulary":[123],"detection,":[125,145],"fine-grained":[126],"text-region":[127],"retrieval,":[128],"attribution":[130],"tasks.":[131],"Our":[132],"results":[133],"show":[134],"can":[138],"wasted":[140],"not":[149],"adequately":[150],"embeddings,":[153],"describing":[155],"classes":[156],"by":[157],"only":[158],"their":[159],"ineffective.":[162],"A":[163],"viable":[164],"strategy":[165],"find":[168],"increase":[170],"benefits":[171],"contrastive":[175],"with":[177],"adjective-based":[178],"negative":[179],"captions.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}