{"id":"https://openalex.org/W6943775335","doi":"https://doi.org/10.17615/xng7-nb97","title":"Language and Perceptual Categorization in Computational Visual Recognition","display_name":"Language and Perceptual Categorization in Computational Visual Recognition","publication_year":2019,"publication_date":"2019-08-08","ids":{"openalex":"https://openalex.org/W6943775335","doi":"https://doi.org/10.17615/xng7-nb97"},"language":"en","primary_location":{"id":"pmh:oai:cdr.lib.unc.edu:uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","is_oa":true,"landing_page_url":"https://cdr.lib.unc.edu/record/uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","pdf_url":"https://cdr.lib.unc.edu/record/uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","source":{"id":"https://openalex.org/S4306401075","display_name":"Carolina Digital Repository (University of North Carolina at Chapel Hill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://cdr.lib.unc.edu/record/uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ordonez Roman, Vicente","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ordonez Roman, Vicente","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35605268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8325999975204468,"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":0.8325999975204468,"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":0.024299999698996544,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0210999995470047,"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/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.6032000184059143},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5953999757766724},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5407999753952026},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44839999079704285},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4309999942779541},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.4262999892234802},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.40549999475479126},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4043999910354614},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789999842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6266999840736389},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.6032000184059143},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4855000078678131},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.4262999892234802},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39239999651908875},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.30219998955726624},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:cdr.lib.unc.edu:uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","is_oa":true,"landing_page_url":"https://cdr.lib.unc.edu/record/uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","pdf_url":"https://cdr.lib.unc.edu/record/uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","source":{"id":"https://openalex.org/S4306401075","display_name":"Carolina Digital Repository (University of North Carolina at Chapel Hill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.17615/xng7-nb97","is_oa":true,"landing_page_url":"https://doi.org/10.17615/xng7-nb97","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:cdr.lib.unc.edu:uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","is_oa":true,"landing_page_url":"https://cdr.lib.unc.edu/record/uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","pdf_url":"https://cdr.lib.unc.edu/record/uuid:188ef51f-d3dc-4216-97ea-07da5109a1a6","source":{"id":"https://openalex.org/S4306401075","display_name":"Carolina Digital Repository (University of North Carolina at Chapel Hill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8654064536094666,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G884832516","display_name":"RI: Medium: Integrating Humans and Computers for Image and Video Understanding","funder_award_id":"1445409","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6943775335.pdf","grobid_xml":"https://content.openalex.org/works/W6943775335.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Computational":[0],"visual":[1,28,57,76,86,290],"recognition":[2,24,291],"or":[3,39,91,122,203],"giving":[4],"computers":[5],"the":[6,56,96,111,140],"ability":[7],"to":[8,43,95,124,212,252,262,280,288],"understand":[9],"images":[10,106,183],"as":[11,13],"well":[12],"humans":[14],"do":[15],"is":[16,273],"a":[17,32,51,164,179,191,209,238],"core":[18],"problem":[19],"in":[20,47,234,274],"Computer":[21,155],"Vision.":[22],"Traditional":[23],"systems":[25,114,292],"often":[26],"describe":[27,55,247],"content":[29],"by":[30,40,67,151,217,255],"producing":[31],"set":[33],"of":[34,99,105,120,149,182,205,270],"isolated":[35],"labels,":[36],"object":[37],"locations,":[38],"even":[41],"trying":[42],"annotate":[44],"every":[45],"pixel":[46],"an":[48,206,224],"image":[49,171,215],"with":[50,107,184,300],"category.":[52],"People":[53],"instead":[54],"world":[58,74],"using":[59,173,256],"language.":[60],"The":[61,267],"rich":[62],"visually":[63,185,196],"descriptive":[64,186,197],"language":[65,126,143,282],"produced":[66],"people":[68],"incorporates":[69],"information":[70],"from":[71,154,258,285,297],"human":[72,286],"intuition,":[73],"knowledge,":[75],"saliency,":[77],"and":[78,127,144,157,169,208,228,264,283,298],"common":[79],"sense":[80],"that":[81,115,138,293],"go":[82],"beyond":[83],"detecting":[84],"individual":[85],"concepts":[87],"like":[88],"objects,":[89],"attributes,":[90],"scenes.":[92],"Moreover,":[93],"due":[94],"rising":[97],"popularity":[98],"social":[100],"media,":[101],"there":[102],"exist":[103],"billions":[104],"associated":[108],"text":[109],"on":[110,278],"web,":[112],"yet":[113],"can":[116,294],"leverage":[117,281],"this":[118,132,271],"type":[119],"annotations":[121],"try":[123],"connect":[125],"vision":[128,145],"are":[129],"scarce.":[130],"In":[131],"dissertation,":[133],"we":[134,189,222,246],"propose":[135],"new":[136],"approaches":[137],"explore":[139],"connections":[141],"between":[142],"at":[146,237],"several":[147],"levels":[148],"detail":[150],"combining":[152],"techniques":[153],"Vision":[156],"Natural":[158],"Language":[159],"Understanding.":[160],"We":[161],"first":[162],"present":[163],"data-driven":[165],"technique":[166,211],"for":[167,193,199,226,232,249],"understanding":[168],"generating":[170,229],"descriptions":[172,216],"natural":[174,235],"language,":[175],"including":[176],"automatically":[177],"collecting":[178,227],"big-scale":[180],"dataset":[181],"captions.":[187],"Then":[188],"introduce":[190,223],"system":[192],"retrieving":[194],"short":[195,219],"phrases":[198],"describing":[200],"some":[201],"part":[202],"aspect":[204],"image,":[207],"simple":[210],"generate":[213],"full":[214],"stitching":[218],"phrases.":[220],"Next":[221],"approach":[225],"referring":[230],"expressions":[231],"objects":[233,254],"scenes":[236],"much":[239],"larger":[240],"scale":[241],"than":[242],"previous":[243],"studies.":[244],"Finally,":[245],"methods":[248],"learning":[250],"how":[251,279],"name":[253],"intuitions":[257,284],"perceptual":[259],"categorization":[260],"related":[261],"basic-level":[263],"entry-level":[265],"categories.":[266],"main":[268],"contribution":[269],"thesis":[272],"advancing":[275],"our":[276],"knowledge":[277],"perception":[287],"create":[289],"better":[295],"learn":[296],"communicate":[299],"people.":[301]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}