{"id":"https://openalex.org/W4387010030","doi":"https://doi.org/10.1109/tcsvt.2023.3318839","title":"Un-Gaze: A Unified Transformer for Joint Gaze-Location and Gaze-Object Detection","display_name":"Un-Gaze: A Unified Transformer for Joint Gaze-Location and Gaze-Object Detection","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387010030","doi":"https://doi.org/10.1109/tcsvt.2023.3318839"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3318839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3318839","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5043611587","display_name":"Danyang Tu","orcid":"https://orcid.org/0000-0001-9632-9131"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Danyang Tu","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048353325","display_name":"Wei Shen","orcid":"https://orcid.org/0000-0002-1235-598X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Shen","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044700284","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0001-8162-1949"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002277899","display_name":"Chang Wen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Changwen Chen","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043611587"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.1928,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80020913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":"5","first_page":"3271","last_page":"3285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9966999888420105,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.9214471578598022},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7628957033157349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6561353802680969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6463581919670105},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4708012342453003},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44908401370048523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1547648310661316},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.1158476173877716}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.9214471578598022},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7628957033157349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6561353802680969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6463581919670105},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4708012342453003},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44908401370048523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1547648310661316},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.1158476173877716},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3318839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3318839","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1393589877","display_name":null,"funder_award_id":"21ZR1432200","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G3386619338","display_name":null,"funder_award_id":"62301316","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4024070150","display_name":null,"funder_award_id":"2023TQ0212","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4054117750","display_name":null,"funder_award_id":"61831015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G81657677","display_name":null,"funder_award_id":"62176159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8668751174","display_name":null,"funder_award_id":"62225112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1861492603","https://openalex.org/W2002781701","https://openalex.org/W2027879843","https://openalex.org/W2064675550","https://openalex.org/W2130313210","https://openalex.org/W2146103513","https://openalex.org/W2194775991","https://openalex.org/W2288514685","https://openalex.org/W2468114283","https://openalex.org/W2778268008","https://openalex.org/W2798558457","https://openalex.org/W2807663718","https://openalex.org/W2883284130","https://openalex.org/W2917092108","https://openalex.org/W2952116933","https://openalex.org/W2962766617","https://openalex.org/W2963556443","https://openalex.org/W2963985934","https://openalex.org/W2976818183","https://openalex.org/W2984401364","https://openalex.org/W2993592664","https://openalex.org/W2998221292","https://openalex.org/W2999173367","https://openalex.org/W3018757597","https://openalex.org/W3024190281","https://openalex.org/W3035735638","https://openalex.org/W3041498386","https://openalex.org/W3096609285","https://openalex.org/W3129576076","https://openalex.org/W3154013571","https://openalex.org/W3166543103","https://openalex.org/W3170841864","https://openalex.org/W3171125843","https://openalex.org/W3174359952","https://openalex.org/W3188642398","https://openalex.org/W4214893857","https://openalex.org/W4285116117","https://openalex.org/W4292692470","https://openalex.org/W4304086133","https://openalex.org/W4312287801","https://openalex.org/W4312510569","https://openalex.org/W4312979210","https://openalex.org/W4313061846","https://openalex.org/W4385245566","https://openalex.org/W6674616764","https://openalex.org/W6686360814","https://openalex.org/W6757817989","https://openalex.org/W6764703237","https://openalex.org/W6778161298","https://openalex.org/W6784094891","https://openalex.org/W6838769457","https://openalex.org/W6947681574"],"related_works":["https://openalex.org/W2385108104","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,59,141,172],"efficient":[4],"and":[5,14,27,45,79,91,97,132,147,161,169,193,281],"effective":[6],"method":[7],"for":[8,63,107,209,229,243],"joint":[9],"gaze":[10,15,20,70,81,89,92,114,163,236,259],"location":[11,90],"detection":[12,17,72,110,116],"(GL-D)":[13],"object":[16,61,93],"(GO-D),":[18],"i.e.,":[19],"following":[21,71,109,115,237],"detection.":[22],"Current":[23],"approaches":[24],"frame":[25],"GL-D":[26,52,131],"GO-D":[28,133],"as":[29,74,211,213,247,288],"two":[30],"separate":[31],"tasks,":[32],"employing":[33],"a":[34,50,95,135,152,178,194,214,244,270],"multi-stage":[35],"framework":[36],"where":[37],"human":[38,76,88,148,162,245,290],"head":[39,77,149,246],"crops":[40],"must":[41],"first":[42,126],"be":[43,47],"detected":[44],"then":[46],"fed":[48],"into":[49],"subsequent":[51],"sub-network,":[53],"which":[54],"is":[55],"further":[56],"followed":[57],"by":[58,118],"additional":[60,121],"detector":[62],"GO-D.":[64,230],"In":[65],"contrast,":[66],"we":[67,103],"reframe":[68],"the":[69,113,125,156,165,241,251,282,289],"task":[73],"detecting":[75,235],"locations":[78],"their":[80],"followings":[82,260],"simultaneously,":[83,261],"aiming":[84],"at":[85],"jointly":[86],"detect":[87],"in":[94,134,171,263,279],"unified":[96,127],"single-stage":[98],"pipeline.":[99],"To":[100],"this":[101],"end,":[102],"propose":[104],"GTR,":[105],"short":[106],"Gaze":[108],"TRansformer,":[111],"streamlining":[112],"pipeline":[117],"eliminating":[119],"all":[120],"components,":[122],"leading":[123],"to":[124,240,253],"paradigm":[128],"that":[129],"unites":[130],"fully":[136],"end-to-end":[137],"manner.":[138],"GTR":[139,176,249,267],"enables":[140],"iterative":[142],"interaction":[143],"between":[144],"holistic":[145],"semantics":[146],"features":[150],"through":[151],"hierarchical":[153],"structure,":[154],"inferring":[155],"relations":[157],"of":[158,257],"salient":[159],"objects":[160],"from":[164],"global":[166],"image":[167],"context":[168],"resulting":[170,262],"impressive":[173],"accuracy.":[174],"Concretely,":[175],"achieves":[177],"12.1":[179],"mAP":[180,196,216],"gain":[181,197],"(":[182,198,218],"<inline-formula":[183,199,219,271],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[184,200,220,272],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[185,201,221,273],"<tex-math":[186,202,222,274],"notation=\"LaTeX\">$\\mathbf":[187,203,223],"{25.1}\\%$":[188],"</tex-math></inline-formula>":[189,205,225,277],")":[190,206,226],"on":[191,207,227],"GazeFollowing":[192],"18.2":[195],"{43.3\\%}$":[204],"VideoAttentionTarget":[208],"GL-D,":[210],"well":[212],"19":[215],"improvement":[217,278],"{45.2\\%}$":[224],"GOO-Real":[228],"Meanwhile,":[231],"unlike":[232],"existing":[233],"systems":[234],"sequentially":[238],"due":[239],"need":[242],"input,":[248],"has":[250],"flexibility":[252],"comprehend":[254],"any":[255],"number":[256,291],"people\u2019s":[258],"high":[264],"efficiency.":[265],"Specifically,":[266],"introduces":[268],"over":[269],"notation=\"LaTeX\">$\\times":[275],"9$":[276],"FPS":[280],"relative":[283],"gap":[284],"becomes":[285],"more":[286],"pronounced":[287],"grows.":[292]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}