{"id":"https://openalex.org/W4408347348","doi":"https://doi.org/10.1109/icassp49660.2025.10890631","title":"Gaze-GZ: Generalized Gaze Estimation with Multi-scale Gaze Zone Prediction","display_name":"Gaze-GZ: Generalized Gaze Estimation with Multi-scale Gaze Zone Prediction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347348","doi":"https://doi.org/10.1109/icassp49660.2025.10890631"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5101631994","display_name":"Zheng Gao","orcid":"https://orcid.org/0000-0001-5541-8840"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Gao","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103370293","display_name":"Puneet Kumar","orcid":"https://orcid.org/0009-0005-2079-6813"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Puneet Kumar","raw_affiliation_strings":["University of Oulu,The Center for Machine Vision and Signal Analysis,Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu,The Center for Machine Vision and Signal Analysis,Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079383053","display_name":"Hao Zou","orcid":"https://orcid.org/0000-0002-6000-6936"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zou","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101691493","display_name":"Xiaobai Li","orcid":"https://orcid.org/0000-0003-4519-7823"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobai Li","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101631994"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0393953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9987000226974487,"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":0.9987000226974487,"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/T10542","display_name":"Vestibular and auditory disorders","score":0.9621000289916992,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9398000240325928,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.9524033069610596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7312998175621033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6373531222343445},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6100860238075256},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5957410931587219},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4634532630443573},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.14295339584350586},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.1079748272895813}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.9524033069610596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312998175621033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373531222343445},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6100860238075256},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5957410931587219},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4634532630443573},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.14295339584350586},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1079748272895813}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2042906110","https://openalex.org/W2194775991","https://openalex.org/W2557669140","https://openalex.org/W2765629358","https://openalex.org/W2963168418","https://openalex.org/W2981101532","https://openalex.org/W2986102820","https://openalex.org/W3030681249","https://openalex.org/W3031409315","https://openalex.org/W3096147990","https://openalex.org/W3109635165","https://openalex.org/W3134723273","https://openalex.org/W3136078915","https://openalex.org/W3185469516","https://openalex.org/W4382239984","https://openalex.org/W4391853684","https://openalex.org/W4392904340","https://openalex.org/W4393147780","https://openalex.org/W4393153719","https://openalex.org/W4393178467","https://openalex.org/W4395470955","https://openalex.org/W4405269876"],"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":{"Gaze":[0],"estimation":[1,115],"models":[2],"often":[3],"experience":[4],"significant":[5],"performance":[6],"degradation":[7],"on":[8,18],"cross-domain":[9],"tests.":[10],"Existing":[11],"methods":[12],"enforce":[13],"the":[14,62,71,76,83,95,106,111],"model":[15],"to":[16,47,80,94],"concentrate":[17],"isolating":[19],"gaze-pertinent":[20],"features":[21,85],"by":[22],"filtering":[23],"out":[24],"irrelevant":[25],"ones.":[26],"This":[27],"paper":[28],"proposes":[29],"an":[30,44],"advanced":[31],"generalized":[32,113],"framework":[33],"for":[34],"gaze":[35,40,64,114],"estimation,":[36],"which":[37],"employs":[38],"multi-scale":[39],"zone":[41,59,88],"prediction":[42],"as":[43],"auxiliary":[45],"task":[46],"improve":[48],"generalization":[49],"capabilities.":[50],"Specifically,":[51],"each":[52,87],"facial":[53],"image":[54],"is":[55],"assigned":[56],"a":[57],"discrete":[58],"sub-label,":[60],"alongside":[61],"continuous":[63],"direction":[65],"label.":[66],"In":[67],"addition,":[68],"we":[69],"introduce":[70],"triplet":[72],"loss":[73],"module":[74],"and":[75,92],"feature":[77],"consistency":[78],"branch":[79],"ensure":[81],"that":[82,105],"extracted":[84],"within":[86],"maintain":[89],"ordered":[90],"embeddings":[91],"robustness":[93],"environmental":[96],"variations,":[97],"respectively.":[98],"The":[99,117],"results":[100],"from":[101],"comprehensive":[102],"experiments":[103],"reveal":[104],"proposed":[107],"method":[108],"outperforms":[109],"all":[110],"state-of-the-art":[112],"methods.":[116],"code":[118],"will":[119],"be":[120],"available":[121],"at":[122],"github.":[123]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}