{"id":"https://openalex.org/W3092450762","doi":"https://doi.org/10.1145/3415220","title":"Vision Skills Needed to Answer Visual Questions","display_name":"Vision Skills Needed to Answer Visual Questions","publication_year":2020,"publication_date":"2020-10-14","ids":{"openalex":"https://openalex.org/W3092450762","doi":"https://doi.org/10.1145/3415220","mag":"3092450762"},"language":"en","primary_location":{"id":"doi:10.1145/3415220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3415220","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3415220","source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3415220","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaoyu Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaoyu Zeng","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanan Wang","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tai-Yin Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tai-Yin Chiu","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nilavra Bhattacharya","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nilavra Bhattacharya","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":null,"display_name":"Danna Gurari","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danna Gurari","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.8832,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.76922439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"4","issue":"CSCW2","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9221000075340271,"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":0.9221000075340271,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.012799999676644802,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6326000094413757},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5799000263214111},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4729999899864197},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3882000148296356},{"id":"https://openalex.org/keywords/turing-test","display_name":"Turing test","score":0.29820001125335693},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.29739999771118164}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6326000094413757},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5234000086784363},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4377000033855438},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3885999917984009},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3483000099658966},{"id":"https://openalex.org/C577917","wikidata":"https://www.wikidata.org/wiki/Q189223","display_name":"Turing test","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C552651612","wikidata":"https://www.wikidata.org/wiki/Q7328862","display_name":"Visual thinking","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C2778750949","wikidata":"https://www.wikidata.org/wiki/Q1156763","display_name":"Visual literacy","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3415220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3415220","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3415220","source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.03160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.03160","pdf_url":"https://arxiv.org/pdf/2010.03160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3415220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3415220","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3415220","source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6413178892","display_name":"CRII: CHS: Predicting When, Why, and How Multiple People Will Disagree when Answering a Visual Question","funder_award_id":"1755593","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8079694169","display_name":null,"funder_award_id":"IIS-1755593","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092450762.pdf","grobid_xml":"https://content.openalex.org/works/W3092450762.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W141352744","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1983927101","https://openalex.org/W2090048052","https://openalex.org/W2090254904","https://openalex.org/W2095781211","https://openalex.org/W2099463451","https://openalex.org/W2141880430","https://openalex.org/W2194775991","https://openalex.org/W2442626797","https://openalex.org/W2471094925","https://openalex.org/W2529436507","https://openalex.org/W2610525153","https://openalex.org/W2611577320","https://openalex.org/W2745461083","https://openalex.org/W2791213089","https://openalex.org/W2810059778","https://openalex.org/W2896108493","https://openalex.org/W2899349505","https://openalex.org/W2963573141","https://openalex.org/W2963954913","https://openalex.org/W2964034671","https://openalex.org/W2964138343","https://openalex.org/W2980540915","https://openalex.org/W2982974767","https://openalex.org/W2983035945","https://openalex.org/W2985011762","https://openalex.org/W2986466127","https://openalex.org/W2986641837","https://openalex.org/W2986685865","https://openalex.org/W2988450373","https://openalex.org/W2998746484","https://openalex.org/W3034716173"],"related_works":[],"abstract_inverted_index":{"The":[0],"task":[1,95],"of":[2,79,96,116,119,125],"answering":[3,142],"questions":[4,67],"about":[5,107,134],"images":[6],"has":[7],"garnered":[8],"attention":[9],"as":[10,20,22],"a":[11,23,93,105,132],"practical":[12],"service":[13],"for":[14,27,43,53,82,137],"assisting":[15],"populations":[16],"with":[17,131],"visual":[18,24,66,140],"impairments":[19],"well":[21],"Turing":[25],"test":[26],"the":[28,38,51,77,123,126,139],"artificial":[29],"intelligence":[30],"community.":[31,128],"Our":[32,110],"first":[33],"aim":[34],"is":[35],"to":[36,103],"identify":[37],"common":[39],"vision":[40,55,99],"skills":[41,81,100],"needed":[42,102],"both":[44,72,83,88],"scenarios.":[45,73],"To":[46],"do":[47],"so,":[48],"we":[49,91],"analyze":[50],"need":[52],"four":[54],"skills--object":[56],"recognition,":[57,59,61],"text":[58],"color":[60],"and":[62,85,122],"counting--on":[63],"over":[64],"27,000":[65],"from":[68],"two":[69],"datasets":[70],"representing":[71],"We":[74,129],"next":[75],"quantify":[76],"difficulty":[78],"these":[80],"humans":[84],"computers":[86],"on":[87],"datasets.":[89],"Finally,":[90],"propose":[92],"novel":[94],"predicting":[97],"what":[98],"are":[101],"answer":[104],"question":[106,141],"an":[108],"image.":[109],"results":[111],"reveal":[112],"(mis)matches":[113],"between":[114],"aims":[115],"real":[117],"users":[118],"such":[120],"services":[121],"focus":[124],"AI":[127],"conclude":[130],"discussion":[133],"future":[135],"directions":[136],"addressing":[138],"task.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2020-10-15T00:00:00"}