{"id":"https://openalex.org/W7162760017","doi":"https://doi.org/10.1145/3797246.3805859","title":"Gaze-informed Object Sequences for Egocentric Action Recognition using Deep Learning","display_name":"Gaze-informed Object Sequences for Egocentric Action Recognition using Deep Learning","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162760017","doi":"https://doi.org/10.1145/3797246.3805859"},"language":null,"primary_location":{"id":"doi:10.1145/3797246.3805859","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797246.3805859","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Symposium on Eye Tracking Research and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797246.3805859","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025165645","display_name":"Nora Castner","orcid":"https://orcid.org/0000-0002-6771-7693"},"institutions":[{"id":"https://openalex.org/I1302207122","display_name":"Carl Zeiss (Germany)","ror":"https://ror.org/02mp31p96","country_code":"DE","type":"company","lineage":["https://openalex.org/I1302207122"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nora Jane Castner","raw_affiliation_strings":["Zeiss Vision Science Lab, Zeiss, Aalen, Baden-W\u00fcrttemberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6771-7693","affiliations":[{"raw_affiliation_string":"Zeiss Vision Science Lab, Zeiss, Aalen, Baden-W\u00fcrttemberg, Germany","institution_ids":["https://openalex.org/I1302207122"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102139936","display_name":"Zhengyu Su","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Zhengyu Su","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0009-0005-4773-5033","affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060895798","display_name":"Siegfried Wahl","orcid":"https://orcid.org/0000-0003-3437-6711"},"institutions":[{"id":"https://openalex.org/I1302207122","display_name":"Carl Zeiss (Germany)","ror":"https://ror.org/02mp31p96","country_code":"DE","type":"company","lineage":["https://openalex.org/I1302207122"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Siegfried Wahl","raw_affiliation_strings":["University of T\u00fcbingen, Institute for Ophthalmic Research, T\u00fcbingen, Germany and Carl Zeiss Vision International GmbH, Aalen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3437-6711","affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, Institute for Ophthalmic Research, T\u00fcbingen, Germany and Carl Zeiss Vision International GmbH, Aalen, Germany","institution_ids":["https://openalex.org/I1302207122"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5917828,"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":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.47760000824928284,"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":0.47760000824928284,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.16949999332427979,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.08460000157356262,"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/pipeline","display_name":"Pipeline (software)","score":0.7498000264167786},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6248999834060669},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5181999802589417},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5092999935150146},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.507099986076355},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47360000014305115},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.45350000262260437}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.821399986743927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631999850273132},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7498000264167786},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5687999725341797},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5181999802589417},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4124999940395355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797246.3805859","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797246.3805859","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Symposium on Eye Tracking Research and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797246.3805859","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797246.3805859","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Symposium on Eye Tracking Research and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7157626748085022,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2109864487","https://openalex.org/W2140277155","https://openalex.org/W2406467511","https://openalex.org/W2895299763","https://openalex.org/W2899222355","https://openalex.org/W2955336980","https://openalex.org/W3021066554","https://openalex.org/W3048602385","https://openalex.org/W3089286977","https://openalex.org/W4281729400","https://openalex.org/W4281876141","https://openalex.org/W4317829471","https://openalex.org/W4390828663","https://openalex.org/W4396821506","https://openalex.org/W4402671448","https://openalex.org/W4402716047","https://openalex.org/W4402904246","https://openalex.org/W4410790619"],"related_works":[],"abstract_inverted_index":{"We":[0,61],"propose":[1],"a":[2,24,45,73],"gaze-informed,":[3],"object-centric":[4,100],"sequence":[5,101],"representation":[6],"pipeline":[7,83,111],"for":[8,99,132],"egocentric":[9],"action":[10],"recognition":[11],"that":[12],"integrates":[13],"human":[14],"attention":[15,59],"signals":[16],"with":[17,87],"open-vocabulary":[18],"vision-language":[19],"models.":[20],"This":[21],"approach":[22,64],"offers":[23],"time-saving":[25],"alternative":[26],"to":[27,40,44,125],"manual":[28,89,104],"AOI-labeling":[29],"in":[30,118],"dynamic":[31],"scene":[32],"content.":[33],"Gaze":[34],"fixations":[35],"guide":[36],"the":[37,78,108,114,119,133],"YOLO-World":[38,96],"model":[39],"identify":[41],"objects":[42,49],"relevant":[43],"researcher\u2019s":[46],"application.":[47],"Attended":[48],"are":[50],"encoded":[51],"into":[52],"temporally":[53],"ordered":[54],"token":[55],"scanpaths":[56],"representing":[57],"semantic":[58],"structure.":[60],"evaluate":[62],"this":[63],"using":[65,72],"these":[66],"textual":[67],"tokens":[68],"and":[69,93,107],"classifying":[70],"actions":[71,117],"lightweight":[74],"BiGRU":[75,122],"trained":[76],"on":[77],"EGTEA":[79],"Gaze+":[80],"dataset.":[81,120],"The":[82,121],"is":[84],"fully":[85],"automatic":[86],"no":[88],"intervention,":[90],"emphasizing":[91],"automation":[92],"accessibility.":[94],"Overall,":[95],"proves":[97],"viable":[98],"representation,":[102],"reducing":[103],"labeling":[105],"overhead,":[106],"full":[109],"evaluation":[110],"accurately":[112],"recognizes":[113],"most":[115,135],"prominent":[116],"was":[123],"able":[124],"achieve":[126],"mean":[127],"class":[128],"accuracy":[129],"of":[130],"76%":[131],"two":[134],"labeled":[136],"classes.":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-30T00:00:00"}