{"id":"https://openalex.org/W6990434323","doi":null,"title":"3D Gaze Estimation on RGB Images using Vision Transformers","display_name":"3D Gaze Estimation on RGB Images using Vision Transformers","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6990434323"},"language":"en","primary_location":{"id":"pmh:oai:DiVA.org:kth-344302","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-344302","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1844033/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kth.diva-portal.org/smash/get/diva2:1844033/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Jing","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.00039999998989515007,"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/T11448","display_name":"Face recognition and analysis","score":0.0003000000142492354,"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-estimation","display_name":"gaze estimation","score":0.8220000267028809},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.7450000047683716},{"id":"https://openalex.org/keywords/hybrid-cnn-vit-model","display_name":"hybrid CNN-ViT model","score":0.7329999804496765},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9350000023841858},{"id":"https://openalex.org/keywords/rgb-images","display_name":"RGB images","score":0.8679999709129333},{"id":"https://openalex.org/keywords/model-size","display_name":"model size","score":0.4020000100135803},{"id":"https://openalex.org/keywords/human-computer-interaction","display_name":"human-computer interaction","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8465999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7817000150680542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095999717712402},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.66839998960495},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.453000009059906},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40790000557899475},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:DiVA.org:kth-344302","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-344302","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1844033/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-344302","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-344302","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1844033/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6990434323.pdf","grobid_xml":"https://content.openalex.org/works/W6990434323.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2077819131","https://openalex.org/W2112796928","https://openalex.org/W2167020116","https://openalex.org/W2518108298","https://openalex.org/W2735766064","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2961365073","https://openalex.org/W2963542740","https://openalex.org/W2964121744","https://openalex.org/W3037932933","https://openalex.org/W3092462694","https://openalex.org/W3093303082","https://openalex.org/W3094502228","https://openalex.org/W4312996499"],"related_works":["https://openalex.org/W7018764641","https://openalex.org/W6889537526","https://openalex.org/W6991099048","https://openalex.org/W7140878839","https://openalex.org/W4312996499","https://openalex.org/W4410428596","https://openalex.org/W4392668189","https://openalex.org/W4411413257","https://openalex.org/W4402698861","https://openalex.org/W7118877001"],"abstract_inverted_index":{"Gaze":[0],"estimation,":[1,76],"a":[2,102],"vital":[3],"component":[4],"in":[5,167,178],"numerous":[6],"applications":[7],"such":[8,52,127],"as":[9,53,128,191],"humancomputer":[10],"interaction,":[11],"virtual":[12],"reality,":[13],"and":[14,41,136,150,157,225],"driver":[15],"monitoring":[16],"systems,":[17],"is":[18,93],"the":[19,23,47,79,96,120,129,140,161,181,186,192,200,206,212,234,238,248],"process":[20],"of":[21,25,49,90,98,119,142,240],"predicting":[22],"direction":[24],"an":[26,222,241],"individual\u2019s":[27],"gaze.":[28],"The":[29,87],"predominant":[30],"methods":[31,45,58],"for":[32,111],"gaze":[33,68,75,112,131],"estimation":[34,113],"can":[35],"be":[36,233],"broadly":[37],"classified":[38],"into":[39],"intrusive":[40],"nonintrusive":[42],"approaches.":[43],"Intrusive":[44],"necessitate":[46],"use":[48,250],"specialized":[50],"hardware,":[51],"eye":[54],"trackers,":[55],"while":[56],"non-intrusive":[57,80],"leverage":[59],"images":[60],"or":[61,209],"recordings":[62],"obtained":[63],"from":[64],"cameras":[65],"to":[66,94,180,204],"make":[67],"predictions.":[69],"This":[70,217],"thesis":[71],"concentrates":[72],"on":[73,114,125,247],"appearance-based":[74],"specifically":[77],"within":[78],"domain,":[81],"employing":[82],"various":[83],"deep":[84],"learning":[85],"models.":[86],"primary":[88],"focus":[89],"this":[91],"study":[92],"compare":[95],"efficacy":[97],"Vision":[99],"Transformers":[100],"(ViTs),":[101],"recently":[103],"introduced":[104],"architecture,":[105],"with":[106,211],"Convolutional":[107],"Neural":[108],"Networks":[109],"(CNNs)":[110],"RGB":[115],"images.":[116],"Performance":[117],"evaluations":[118],"models":[121],"are":[122,146,165],"conducted":[123],"based":[124],"metrics":[126],"angular":[130],"error,":[132,135],"stimulus":[133],"distance":[134],"model":[137,194,214,243],"size.":[138],"Within":[139],"realm":[141],"ViTs,":[143,152],"two":[144],"variants":[145,164],"explored:":[147],"pure":[148,175],"ViTs":[149,176],"hybrid":[151,187,207],"which":[153],"combine":[154],"both":[155,163],"CNN":[156],"ViT":[158,188,208],"architectures.":[159],"Throughout":[160],"project,":[162],"examined":[166],"different":[168],"sizes.":[169],"Experimental":[170],"results":[171],"demonstrate":[172],"that":[173],"all":[174,196],"underperform":[177],"comparison":[179],"baseline":[182,213],"ResNet-18":[183],"model.":[184],"However,":[185],"consistently":[189],"emerges":[190],"best-performing":[193],"across":[195],"evaluation":[197],"datasets.":[198],"Nonetheless,":[199],"discussion":[201],"regarding":[202],"whether":[203],"deploy":[205],"stick":[210],"remains":[215],"unresolved.":[216],"uncertainty":[218],"arises":[219],"because":[220],"utilizing":[221],"exceedingly":[223],"large":[224],"slow":[226],"model,":[227],"albeit":[228],"highly":[229],"accurate,":[230],"may":[231,244],"not":[232],"optimal":[235],"solution.":[236],"Hence,":[237],"selection":[239],"appropriate":[242],"vary":[245],"depending":[246],"specific":[249],"case.":[251]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}