{"id":"https://openalex.org/W7105670522","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228695","title":"Hybrid Swin Transformer for Appearance Gaze Estimation","display_name":"Hybrid Swin Transformer for Appearance Gaze Estimation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105670522","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228695"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Zhang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhang Cheng","raw_affiliation_strings":["Chongqing Normal University,College of Computer and Information Science,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanxia Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxia Wang","raw_affiliation_strings":["Chongqing Normal University,College of Computer and Information Science,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinliang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinliang Liu","raw_affiliation_strings":["Chongqing Normal University,College of Computer and Information Science,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liang","raw_affiliation_strings":["Chongqing Normal University,College of Computer and Information Science,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fenglin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenglin Huang","raw_affiliation_strings":["Chongqing Normal University,College of Computer and Information Science,China"],"affiliations":[{"raw_affiliation_string":"Chongqing Normal University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I126924076"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126924076"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57360575,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9896000027656555,"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":0.9896000027656555,"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":0.0017000000225380063,"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":0.001500000013038516,"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/transformer","display_name":"Transformer","score":0.7684000134468079},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7454000115394592},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.5465999841690063},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5163000226020813},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5109999775886536},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4481000006198883}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7684000134468079},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7454000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611299991607666},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.5465999841690063},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28610000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C2983447341","wikidata":"https://www.wikidata.org/wiki/Q1413083","display_name":"Model parameter","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4557859003543854,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2027879843","https://openalex.org/W2042906110","https://openalex.org/W2531409750","https://openalex.org/W2557669140","https://openalex.org/W2895535699","https://openalex.org/W2921627265","https://openalex.org/W2964054038","https://openalex.org/W2986102820","https://openalex.org/W2998355285","https://openalex.org/W3096147990","https://openalex.org/W3121523901","https://openalex.org/W3136078915","https://openalex.org/W3138516171","https://openalex.org/W4214588794","https://openalex.org/W4224929143","https://openalex.org/W4312996499","https://openalex.org/W4319300355","https://openalex.org/W4367050083","https://openalex.org/W4383819342","https://openalex.org/W4384694636","https://openalex.org/W4385801423","https://openalex.org/W4387950264","https://openalex.org/W4388624014","https://openalex.org/W4390481633","https://openalex.org/W4390788770","https://openalex.org/W4391306550","https://openalex.org/W4392154306","https://openalex.org/W4393153719","https://openalex.org/W4394593194"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"models":[1],"based":[2,56],"on":[3,57],"the":[4,20,29,51,65,87,95,105,111,116,145,154,161,173],"Swin":[5,30,53,81,101],"Transformer":[6,31],"architecture":[7],"have":[8],"been":[9],"applied":[10],"to":[11,63,109,132,153],"gaze":[12,124],"estimation":[13,125],"tasks,":[14],"effectively":[15],"improving":[16],"their":[17],"performance.":[18],"However,":[19],"large":[21],"number":[22,146,162],"of":[23,28,45,67,92,100,115,147,163],"parameters":[24,148,164],"and":[25,73,103,149,165,169,177],"high":[26],"FLOPs":[27,166],"model":[32,174],"result":[33],"in":[34,123],"significant":[35,138],"computational":[36,150],"resource":[37],"demands,":[38],"limiting":[39],"its":[40,71,121],"application":[41],"scenarios.":[42],"In":[43],"terms":[44],"this":[46,48],"issue,":[47],"paper":[49],"proposes":[50],"Pure":[52],"Transformer(PST-Net)":[54],"model,":[55,79,117],"an":[58],"improved":[59],"Swin-T":[60],"model.":[61],"Furthermore,":[62],"enhance":[64,110],"performance":[66,122,139],"PST-Net":[68],"while":[69],"reducing":[70],"time":[72],"space":[74],"complexity,":[75],"a":[76],"new":[77],"lightweight":[78,176],"Hybrid":[80],"Transformer(HST-Net),":[82],"is":[83],"proposed.":[84],"HST-Net":[85,134,159],"integrates":[86],"powerful":[88],"feature":[89],"extraction":[90],"capabilities":[91,99],"CNNs":[93],"with":[94],"global":[96],"information":[97],"interaction":[98],"Transformers":[102],"improves":[104],"fully":[106],"connected":[107],"layers":[108],"nonlinear":[112],"fitting":[113],"capability":[114],"which":[118],"significantly":[119],"boosts":[120],"tasks.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"compared":[131],"PST-Net,":[133],"not":[135],"only":[136],"achieves":[137],"improvements":[140],"but":[141],"also":[142],"greatly":[143],"reduces":[144,160],"costs.":[151],"Compared":[152],"existing":[155],"state-of-the-art":[156],"method,":[157],"SUGE,":[158],"by":[167],"56.4%":[168],"75.4%,":[170],"respectively,":[171],"making":[172],"more":[175],"achieving":[178],"higher":[179],"accuracy.":[180]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2025-11-14T00:00:00"}