{"id":"https://openalex.org/W7104537841","doi":"https://doi.org/10.1016/j.patcog.2025.112695","title":"Learning-by-generation: Enhancing gaze estimation via controllable generative data and two-stage training","display_name":"Learning-by-generation: Enhancing gaze estimation via controllable generative data and two-stage training","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7104537841","doi":"https://doi.org/10.1016/j.patcog.2025.112695"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2025.112695","doi":"https://doi.org/10.1016/j.patcog.2025.112695","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2025.112695","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2025.112695","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiawei Qin","orcid":"https://orcid.org/0000-0003-1648-9720","observed_orcids":["https://orcid.org/0000-0003-1648-9720"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jiawei Qin","raw_affiliation_strings":["The University of Tokyo, 4-6-1 Komaba, Meguro, 153-8505, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1648-9720","affiliations":[{"raw_affiliation_string":"The University of Tokyo, 4-6-1 Komaba, Meguro, 153-8505, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000184834","display_name":"Xueting Wang","orcid":"https://orcid.org/0000-0002-1009-1095","observed_orcids":["https://orcid.org/0000-0002-1009-1095"]},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xueting Wang","raw_affiliation_strings":["CyberAgent, 2-24-12 Shibuya, Shibuya, 150-6121, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1009-1095","affiliations":[{"raw_affiliation_string":"CyberAgent, 2-24-12 Shibuya, Shibuya, 150-6121, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066894394","display_name":"Yusuke Sugano","orcid":"https://orcid.org/0000-0003-4206-710X","observed_orcids":["https://orcid.org/0000-0003-4206-710X"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Sugano","raw_affiliation_strings":["The University of Tokyo, 4-6-1 Komaba, Meguro, 153-8505, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4206-710X","affiliations":[{"raw_affiliation_string":"The University of Tokyo, 4-6-1 Komaba, Meguro, 153-8505, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":2590,"currency":"USD","value_usd":2590},"apc_paid":{"value":2590,"currency":"USD","value_usd":2590},"fwci":0.4668,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57271263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"172","issue":null,"first_page":"112695","last_page":"112695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9833999872207642,"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":0.9833999872207642,"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/T11448","display_name":"Face recognition and analysis","score":0.00570000009611249,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0010000000474974513,"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":0.9900000095367432},{"id":"https://openalex.org/keywords/appearance-based-gaze-estimation","display_name":"appearance-based gaze estimation","score":0.7929999828338623},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8420000076293945},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.968999981880188},{"id":"https://openalex.org/keywords/two-stage-training","display_name":"two-stage training","score":0.8029999732971191},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.847000002861023},{"id":"https://openalex.org/keywords/noisy-pseudo-labels","display_name":"pseudo-label noise","score":0.9049999713897705},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.722000002861023},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.7049999833106995},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9190000295639038},{"id":"https://openalex.org/keywords/generalization-to-unseen-environments","display_name":"generalization to unseen environments","score":0.7649999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6779999732971191},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.6668999791145325},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.616100013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4399999976158142},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2025.112695","doi":"https://doi.org/10.1016/j.patcog.2025.112695","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2025.112695","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.patcog.2025.112695","doi":"https://doi.org/10.1016/j.patcog.2025.112695","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2025.112695","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2742428180","https://openalex.org/W2765629358","https://openalex.org/W2935252677","https://openalex.org/W3163195584","https://openalex.org/W3178406257","https://openalex.org/W4310827167","https://openalex.org/W4366330698","https://openalex.org/W4372283500","https://openalex.org/W4378474401","https://openalex.org/W4385967950","https://openalex.org/W4388692601","https://openalex.org/W4392904340","https://openalex.org/W4394593194","https://openalex.org/W7084079131"],"related_works":["https://openalex.org/W4403598467","https://openalex.org/W7167054349","https://openalex.org/W7138440852","https://openalex.org/W2299591120","https://openalex.org/W2789328703","https://openalex.org/W2769425103","https://openalex.org/W2894849367","https://openalex.org/W2739694187","https://openalex.org/W4310884550","https://openalex.org/W3033881456"],"abstract_inverted_index":{"Generalization":[0],"to":[1,30,69,74,103],"unseen":[2],"environments":[3],"is":[4,11],"crucial":[5],"in":[6,16,62,77,149],"appearance-based":[7],"gaze":[8,20,37,64,97],"estimation":[9],"but":[10],"primarily":[12],"hindered":[13],"by":[14],"limitations":[15],"appearance":[17,71,100],"diversity":[18],"and":[19,99,122,127,147],"range.":[21],"However,":[22],"collecting":[23],"large-scale":[24],"real":[25],"data":[26,58,92,107,145],"remains":[27],"challenging":[28],"due":[29],"the":[31,131],"inefficiency":[32],"of":[33],"physically":[34],"capturing":[35],"3D":[36],"directions.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,112],"present":[43],"a":[44,84,114],"novel":[45],"fully":[46],"learning-by-generation":[47,133],"pipeline":[48,117,134],"that":[49,118,130],"relies":[50],"exclusively":[51],"on":[52,83],"synthetic":[53,57,106],"data.":[54],"While":[55],"prior":[56],"has":[59],"shown":[60],"promise":[61],"extending":[63],"ranges,":[65],"its":[66],"limited":[67],"ability":[68],"control":[70],"still":[72],"leads":[73],"suboptimal":[75],"performance":[76],"unknown":[78],"environments.":[79],"Our":[80],"approach,":[81],"based":[82],"generative":[85],"adversarial":[86],"network":[87],"(GAN),":[88],"enables":[89],"more":[90],"flexible":[91],"synthesis,":[93],"simultaneously":[94],"addressing":[95],"both":[96,144],"range":[98],"diversity.":[101],"Furthermore,":[102],"effectively":[104],"leverage":[105],"for":[108,143],"improved":[109],"model":[110],"generalization,":[111],"introduce":[113],"two-stage":[115],"training":[116],"mitigates":[119],"domain":[120],"shifts":[121],"pseudo-label":[123],"noise.":[124],"Extensive":[125],"experiments":[126],"analyses":[128],"demonstrate":[129],"proposed":[132],"enhances":[135],"robustness":[136],"across":[137],"various":[138],"scenarios,":[139],"making":[140],"it":[141],"valuable":[142],"augmentation":[146],"pre-training":[148],"transfer":[150],"learning.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-11-10T00:00:00"}