{"id":"https://openalex.org/W4387741824","doi":"https://doi.org/10.1007/s11263-023-01879-7","title":"In the Eye of Transformer: Global\u2013Local Correlation for Egocentric Gaze Estimation and Beyond","display_name":"In the Eye of Transformer: Global\u2013Local Correlation for Egocentric Gaze Estimation and Beyond","publication_year":2023,"publication_date":"2023-10-18","ids":{"openalex":"https://openalex.org/W4387741824","doi":"https://doi.org/10.1007/s11263-023-01879-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/38371492"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-023-01879-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01879-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01879-7.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01879-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037220775","display_name":"Bolin Lai","orcid":"https://orcid.org/0000-0001-7578-7336"},"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":true,"raw_author_name":"Bolin Lai","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA 30308 USA","Georgia Institute of Technology, Atlanta, GA, 30308, USA"],"raw_orcid":"https://orcid.org/0000-0001-7578-7336","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA 30308 USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, 30308, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"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"]},{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA 30308 USA","Meta AI, Menlo Park, CA 94025 USA","Georgia Institute of Technology, Atlanta, GA, 30308, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA 30308 USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Meta AI, Menlo Park, CA 94025 USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I3197470489"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, 30308, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016641535","display_name":"Fiona Ryan","orcid":null},"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":"Fiona Ryan","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA 30308 USA","Georgia Institute of Technology, Atlanta, GA, 30308, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA 30308 USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, 30308, 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":["Georgia Institute of Technology, Atlanta, GA 30308 USA","Georgia Institute of Technology, Atlanta, GA, 30308, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA 30308 USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, 30308, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037220775"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":4.3879,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94693064,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"132","issue":"3","first_page":"854","last_page":"871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9995999932289124,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9779999852180481,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9663000106811523,"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":0.7883466482162476},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7734118103981018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.63686203956604},{"id":"https://openalex.org/keywords/fixation","display_name":"Fixation (population genetics)","score":0.6258214116096497},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6175991296768188},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5080718994140625},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4564928412437439},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44357430934906006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12468701601028442}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883466482162476},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7734118103981018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63686203956604},{"id":"https://openalex.org/C146249460","wikidata":"https://www.wikidata.org/wiki/Q2914991","display_name":"Fixation (population genetics)","level":3,"score":0.6258214116096497},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6175991296768188},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5080718994140625},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4564928412437439},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44357430934906006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12468701601028442},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11263-023-01879-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01879-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01879-7.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmid:38371492","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38371492","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":"International journal of computer vision","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10873248","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10873248","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10873248/pdf/11263_2023_Article_1879.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Int J Comput Vis","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s11263-023-01879-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01879-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01879-7.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G7379550034","display_name":null,"funder_award_id":"R01MH114999","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387741824.pdf"},"referenced_works_count":88,"referenced_works":["https://openalex.org/W250309892","https://openalex.org/W1533861849","https://openalex.org/W1912797782","https://openalex.org/W1947031653","https://openalex.org/W1981276685","https://openalex.org/W2062000228","https://openalex.org/W2135957164","https://openalex.org/W2136668269","https://openalex.org/W2147299944","https://openalex.org/W2468114283","https://openalex.org/W2518108298","https://openalex.org/W2741156154","https://openalex.org/W2757028014","https://openalex.org/W2795307598","https://openalex.org/W2810712262","https://openalex.org/W2883284130","https://openalex.org/W2893375469","https://openalex.org/W2895299763","https://openalex.org/W2900293887","https://openalex.org/W2963685207","https://openalex.org/W2964114039","https://openalex.org/W2979442772","https://openalex.org/W2980565715","https://openalex.org/W2986102820","https://openalex.org/W2990503944","https://openalex.org/W2997004687","https://openalex.org/W2997304642","https://openalex.org/W2997592281","https://openalex.org/W3005401190","https://openalex.org/W3015458609","https://openalex.org/W3022565501","https://openalex.org/W3034287518","https://openalex.org/W3035735638","https://openalex.org/W3043142510","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3101262641","https://openalex.org/W3105966669","https://openalex.org/W3109667662","https://openalex.org/W3121143616","https://openalex.org/W3122006940","https://openalex.org/W3123364653","https://openalex.org/W3126721948","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3163079050","https://openalex.org/W3165924482","https://openalex.org/W3168649818","https://openalex.org/W3170778815","https://openalex.org/W3170841864","https://openalex.org/W3171087525","https://openalex.org/W3172908893","https://openalex.org/W3176436964","https://openalex.org/W3189307944","https://openalex.org/W3194945615","https://openalex.org/W3202477427","https://openalex.org/W3202742610","https://openalex.org/W3203003533","https://openalex.org/W3207447090","https://openalex.org/W3210279979","https://openalex.org/W4214561053","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214893857","https://openalex.org/W4281489207","https://openalex.org/W4285176798","https://openalex.org/W4292794051","https://openalex.org/W4307823382","https://openalex.org/W4312356418","https://openalex.org/W4312461822","https://openalex.org/W4312560592","https://openalex.org/W4312769131","https://openalex.org/W4312785900","https://openalex.org/W4312815172","https://openalex.org/W4312878367","https://openalex.org/W4312928145","https://openalex.org/W4312973165","https://openalex.org/W4312977443","https://openalex.org/W4313118515","https://openalex.org/W4313160444","https://openalex.org/W4321021980","https://openalex.org/W4387741824","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6778443936","https://openalex.org/W6778883912","https://openalex.org/W6802913412","https://openalex.org/W6808229666"],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W3207760378"],"abstract_inverted_index":{"Predicting":[0],"human's":[1],"gaze":[2,34,55,146,185],"from":[3,57,187],"egocentric":[4,33,58,106,188],"videos":[5],"serves":[6,179],"as":[7,74],"a":[8,82,135,144,180],"critical":[9],"role":[10],"for":[11,52,183],"human":[12],"intention":[13],"understanding":[14],"in":[15,195],"daily":[16],"activities.":[17],"In":[18,125],"this":[19,62],"paper,":[20],"we":[21,64],"present":[22],"the":[23,29,39,42,54,66,71,90,93,120,130,151,160],"first":[24],"transformer-based":[25],"model":[26,89,103,133,142],"to":[27,69,87,143,172],"address":[28],"challenging":[30],"problem":[31],"of":[32,92,122,164],"estimation.":[35],"We":[36,100,138,167],"observe":[37],"that":[38,176],"connection":[40],"between":[41],"global":[43,72,94],"scene":[44],"context":[45,73],"and":[46,79,96,113,150],"local":[47,98],"visual":[48,77],"information":[49],"is":[50],"vital":[51],"localizing":[53],"fixation":[56,186],"video":[59,107],"frames.":[60],"To":[61],"end,":[63],"design":[65],"transformer":[67],"encoder":[68],"embed":[70],"one":[75],"additional":[76,170],"token":[78,95],"further":[80],"propose":[81],"novel":[83,145],"global-local":[84,177],"correlation":[85,91,178],"module":[86],"explicitly":[88],"each":[97],"token.":[99],"validate":[101],"our":[102,123,127,141,165,174,196],"on":[104],"two":[105],"datasets":[108],"-":[109],"EGTEA":[110],"Gaze":[111],"+":[112],"Ego4D.":[114],"Our":[115],"detailed":[116],"ablation":[117],"studies":[118],"demonstrate":[119],"benefits":[121],"method.":[124],"addition,":[126],"approach":[128],"exceeds":[129],"previous":[131],"state-of-the-art":[132],"by":[134],"large":[136],"margin.":[137],"also":[139,168],"apply":[140],"saccade/fixation":[147],"prediction":[148],"task":[149],"traditional":[152],"action":[153],"recognition":[154],"problem.":[155],"The":[156],"consistent":[157],"gains":[158],"suggest":[159],"strong":[161],"generalization":[162],"capability":[163],"model.":[166],"provide":[169],"visualizations":[171],"support":[173],"claim":[175],"key":[181],"representation":[182],"predicting":[184],"videos.":[189],"More":[190],"details":[191],"can":[192],"be":[193],"found":[194],"website":[197],"(https://bolinlai.github.io/GLC-EgoGazeEst).":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}