{"id":"https://openalex.org/W3123364653","doi":"https://doi.org/10.1109/tpami.2021.3051319","title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","display_name":"In the Eye of the Beholder: Gaze and Actions in First Person Video","publication_year":2021,"publication_date":"2021-01-15","ids":{"openalex":"https://openalex.org/W3123364653","doi":"https://doi.org/10.1109/tpami.2021.3051319","mag":"3123364653","pmid":"https://pubmed.ncbi.nlm.nih.gov/33449877"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3051319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3051319","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100451141","display_name":"Yin Li","orcid":"https://orcid.org/0000-0003-4173-9453"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yin Li","raw_affiliation_strings":["Department of Biostatistics and Medical Informatics, Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0003-4173-9453","affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Medical Informatics, Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348904","display_name":"Miao Liu","orcid":"https://orcid.org/0000-0002-6650-9972"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["School of Interactive Computing, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6650-9972","affiliations":[{"raw_affiliation_string":"School of Interactive Computing, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002228469","display_name":"James M. Rehg","orcid":"https://orcid.org/0000-0003-1793-5462"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James M. Rehg","raw_affiliation_strings":["School of Interactive Computing, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100451141"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":5.0431,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.9642984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"45","issue":"6","first_page":"6731","last_page":"6747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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":0.9979000091552734,"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/gaze","display_name":"Gaze","score":0.8236814141273499},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.711046040058136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6985911130905151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6842578649520874},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5606985688209534},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3632005751132965}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8236814141273499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.711046040058136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985911130905151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6842578649520874},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5606985688209534},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3632005751132965}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005403","descriptor_name":"Fixation, Ocular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005403","descriptor_name":"Fixation, Ocular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005403","descriptor_name":"Fixation, Ocular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006225","descriptor_name":"Hand","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006225","descriptor_name":"Hand","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006225","descriptor_name":"Hand","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3051319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3051319","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:33449877","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33449877","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3004512051","display_name":null,"funder_award_id":"U54EB020404","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"}],"funders":[{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":121,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W33363299","https://openalex.org/W105287674","https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W1606858007","https://openalex.org/W1744759976","https://openalex.org/W1903029394","https://openalex.org/W1906662973","https://openalex.org/W1910566948","https://openalex.org/W1912797782","https://openalex.org/W1913984289","https://openalex.org/W1931090275","https://openalex.org/W1940585053","https://openalex.org/W1944615693","https://openalex.org/W1947050545","https://openalex.org/W1947481528","https://openalex.org/W1948812921","https://openalex.org/W1970629627","https://openalex.org/W1983705368","https://openalex.org/W1990930131","https://openalex.org/W2016053056","https://openalex.org/W2019660985","https://openalex.org/W2022732461","https://openalex.org/W2055302526","https://openalex.org/W2068020527","https://openalex.org/W2070999216","https://openalex.org/W2071711566","https://openalex.org/W2089505226","https://openalex.org/W2095705004","https://openalex.org/W2102605133","https://openalex.org/W2126574503","https://openalex.org/W2126579184","https://openalex.org/W2136668269","https://openalex.org/W2144764737","https://openalex.org/W2147806277","https://openalex.org/W2149276562","https://openalex.org/W2155268664","https://openalex.org/W2162762857","https://openalex.org/W2163915297","https://openalex.org/W2164084182","https://openalex.org/W2165605600","https://openalex.org/W2167020116","https://openalex.org/W2167626157","https://openalex.org/W2212494831","https://openalex.org/W2219155316","https://openalex.org/W2235034809","https://openalex.org/W2282481780","https://openalex.org/W2293655572","https://openalex.org/W2337252826","https://openalex.org/W2338803139","https://openalex.org/W2342662179","https://openalex.org/W2432964524","https://openalex.org/W2461911683","https://openalex.org/W2487442924","https://openalex.org/W2507009361","https://openalex.org/W2546006597","https://openalex.org/W2560474170","https://openalex.org/W2625366777","https://openalex.org/W2737602873","https://openalex.org/W2741156154","https://openalex.org/W2784439217","https://openalex.org/W2795307598","https://openalex.org/W2798963049","https://openalex.org/W2799087757","https://openalex.org/W2883429621","https://openalex.org/W2883534172","https://openalex.org/W2895299763","https://openalex.org/W2897762477","https://openalex.org/W2920582597","https://openalex.org/W2947084868","https://openalex.org/W2950630404","https://openalex.org/W2955874753","https://openalex.org/W2962934715","https://openalex.org/W2962960500","https://openalex.org/W2963082988","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963298379","https://openalex.org/W2963524571","https://openalex.org/W2963601560","https://openalex.org/W2963791050","https://openalex.org/W2964037671","https://openalex.org/W2964072322","https://openalex.org/W2964222622","https://openalex.org/W2964260135","https://openalex.org/W2971680695","https://openalex.org/W2972073579","https://openalex.org/W2980037812","https://openalex.org/W2980096197","https://openalex.org/W2981851019","https://openalex.org/W2982198876","https://openalex.org/W2984287396","https://openalex.org/W2988630963","https://openalex.org/W2990503944","https://openalex.org/W2993447238","https://openalex.org/W2994662721","https://openalex.org/W2995264981","https://openalex.org/W3043142510","https://openalex.org/W3098028994","https://openalex.org/W4246193833","https://openalex.org/W6600983433","https://openalex.org/W6635262810","https://openalex.org/W6637373629","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6674616764","https://openalex.org/W6676662276","https://openalex.org/W6682864246","https://openalex.org/W6684983439","https://openalex.org/W6687045409","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6748257475","https://openalex.org/W6749916090","https://openalex.org/W6750355821","https://openalex.org/W6753924131","https://openalex.org/W6754484989","https://openalex.org/W6764057784","https://openalex.org/W6770820890","https://openalex.org/W6781951202"],"related_works":["https://openalex.org/W2385108104","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"We":[0,103],"address":[1],"the":[2,19,35,54,65,85,116,140],"task":[3],"of":[4,21,118],"jointly":[5],"determining":[6],"what":[7],"a":[8,25,69,89,100,135,143],"person":[9],"is":[10,126],"doing":[11],"and":[12,49,77,92,133],"where":[13],"they":[14],"are":[15],"looking":[16],"based":[17],"on":[18,128,169],"analysis":[20],"video":[22],"captured":[23],"by":[24,142],"headworn":[26],"camera.":[27],"To":[28],"facilitate":[29],"our":[30,129,151],"research,":[31],"we":[32,67,148],"first":[33],"introduce":[34],"EGTEA":[36,130],"Gaze+":[37,131],"dataset.":[38],"Our":[39,82,124],"dataset":[40,132],"comes":[41],"with":[42],"videos,":[43],"gaze":[44,75,87],"tracking":[45],"data,":[46],"hand":[47],"masks":[48],"action":[50,78,122,171],"annotations,":[51],"thereby":[52],"providing":[53],"most":[55],"comprehensive":[56],"benchmark":[57],"for":[58,73,121],"First":[59],"Person":[60],"Vision":[61],"(FPV).":[62],"Moving":[63],"beyond":[64],"dataset,":[66],"propose":[68],"novel":[70],"deep":[71,101],"model":[72,152],"joint":[74],"estimation":[76],"recognition":[79],"in":[80,99],"FPV.":[81],"method":[83,125],"describes":[84],"participant's":[86],"as":[88],"probabilistic":[90],"variable":[91],"models":[93],"its":[94],"distribution":[95],"using":[96,163],"stochastic":[97,108],"units":[98],"network.":[102],"further":[104],"sample":[105],"from":[106],"these":[107],"units,":[109],"generating":[110],"an":[111],"attention":[112],"map":[113],"to":[114,156],"guide":[115],"aggregation":[117],"visual":[119],"features":[120],"recognition.":[123,172],"evaluated":[127],"achieves":[134],"performance":[136],"level":[137],"that":[138,150],"exceeds":[139],"state-of-the-art":[141,167],"significant":[144],"margin.":[145],"More":[146],"importantly,":[147],"demonstrate":[149],"can":[153],"be":[154],"applied":[155],"larger":[157],"scale":[158],"FPV":[159,170],"dataset-EPIC-Kitchens":[160],"even":[161],"without":[162],"gaze,":[164],"offering":[165],"new":[166],"results":[168]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}
