{"id":"https://openalex.org/W4385568420","doi":"https://doi.org/10.1145/3580305.3599312","title":"Domain-Guided Spatio-Temporal Self-Attention for Egocentric 3D Pose Estimation","display_name":"Domain-Guided Spatio-Temporal Self-Attention for Egocentric 3D Pose Estimation","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568420","doi":"https://doi.org/10.1145/3580305.3599312"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599312","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599312","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599312","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599312","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005464645","display_name":"Jinman Park","orcid":"https://orcid.org/0009-0003-0870-8185"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jinman Park","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0003-0870-8185","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022552027","display_name":"Kimathi Kaai","orcid":"https://orcid.org/0009-0004-2034-2638"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kimathi Kaai","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0004-2034-2638","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012642050","display_name":"Saad Hossain","orcid":"https://orcid.org/0009-0006-9844-8437"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Saad Hossain","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0006-9844-8437","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091315994","display_name":"Norikatsu Sumi","orcid":"https://orcid.org/0000-0002-8716-1565"},"institutions":[{"id":"https://openalex.org/I4210110524","display_name":"Nissan (Japan)","ror":"https://ror.org/01nks1c62","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110524"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norikatsu Sumi","raw_affiliation_strings":["Nissan Motor Corporation, Yokohama, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8716-1565","affiliations":[{"raw_affiliation_string":"Nissan Motor Corporation, Yokohama, Japan","institution_ids":["https://openalex.org/I4210110524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018625427","display_name":"Sirisha Rambhatla","orcid":"https://orcid.org/0000-0002-9389-727X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sirisha Rambhatla","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9389-727X","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078015739","display_name":"Paul Fieguth","orcid":"https://orcid.org/0000-0001-7260-2260"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Paul Fieguth","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7260-2260","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0105,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78389295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1837","last_page":"1849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9941999912261963,"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":0.9937000274658203,"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/id-ego-and-super-ego","display_name":"Id, ego and super-ego","score":0.7711964845657349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724003255367279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6201173663139343},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5546224117279053},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.522947371006012},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4618898928165436},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.43129879236221313},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34066063165664673},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15927207469940186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1508503258228302},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0730975866317749},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06999805569648743}],"concepts":[{"id":"https://openalex.org/C9180747","wikidata":"https://www.wikidata.org/wiki/Q486893","display_name":"Id, ego and super-ego","level":2,"score":0.7711964845657349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724003255367279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6201173663139343},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5546224117279053},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.522947371006012},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4618898928165436},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43129879236221313},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34066063165664673},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15927207469940186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1508503258228302},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0730975866317749},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06999805569648743},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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:10.1145/3580305.3599312","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599312","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599312","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599312","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599312","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599312","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385568420.pdf","grobid_xml":"https://content.openalex.org/works/W4385568420.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1905368000","https://openalex.org/W2024165284","https://openalex.org/W2080873731","https://openalex.org/W2101032778","https://openalex.org/W2135533529","https://openalex.org/W2194775991","https://openalex.org/W2554247908","https://openalex.org/W2573854917","https://openalex.org/W2583372902","https://openalex.org/W2604375920","https://openalex.org/W2605947573","https://openalex.org/W2612706635","https://openalex.org/W2792380836","https://openalex.org/W2792747672","https://openalex.org/W2798646183","https://openalex.org/W2809890486","https://openalex.org/W2916798096","https://openalex.org/W2962896489","https://openalex.org/W2963592930","https://openalex.org/W2963688992","https://openalex.org/W2972662547","https://openalex.org/W2981660954","https://openalex.org/W2982627166","https://openalex.org/W2989465897","https://openalex.org/W2990837443","https://openalex.org/W2998027150","https://openalex.org/W3034448411","https://openalex.org/W3034677259","https://openalex.org/W3036644940","https://openalex.org/W3049455300","https://openalex.org/W3106838237","https://openalex.org/W3119670522","https://openalex.org/W3126541466","https://openalex.org/W3132607124","https://openalex.org/W3136525061","https://openalex.org/W3160439519","https://openalex.org/W3173415456","https://openalex.org/W3213740329","https://openalex.org/W4214518393","https://openalex.org/W4214759957","https://openalex.org/W4312252130","https://openalex.org/W4312417903"],"related_works":["https://openalex.org/W4317827682","https://openalex.org/W2384047230","https://openalex.org/W2349664984","https://openalex.org/W129516394","https://openalex.org/W3151918114","https://openalex.org/W2912578624","https://openalex.org/W2949426115","https://openalex.org/W2359694826","https://openalex.org/W2742105664","https://openalex.org/W2971369648"],"abstract_inverted_index":{"Vision-based":[0],"ego-centric":[1,104],"3D":[2],"human":[3,159],"pose":[4,160],"estimation":[5,161],"(ego-HPE)":[6],"is":[7,168],"essential":[8],"to":[9,50,72,97,148],"support":[10],"critical":[11],"applications":[12],"of":[13,136,145],"xR-technologies.":[14],"However,":[15],"severe":[16],"self-occlusions":[17,77],"and":[18,69,76],"strong":[19],"distortion":[20],"introduced":[21],"by":[22,53],"the":[23,27,95,110,119,124,134,142,163],"fish-eye":[24],"view":[25],"from":[26],"head":[28],"mounted":[29],"camera,":[30],"make":[31],"ego-HPE":[32,126],"extremely":[33],"challenging.":[34],"To":[35],"address":[36,73],"these":[37],"challenges,":[38],"we":[39,57,81,139],"propose":[40],"a":[41,83,115,130],"domain-guided":[42,55],"spatio-temporal":[43,70,100],"transformer":[44],"model":[45,147],"that":[46],"leverages":[47],"information":[48,101],"specific":[49],"ego-views.":[51],"Powered":[52],"this":[54],"transformer,":[56],"build":[58],"Egocentric":[59],"Spatio-Temporal":[60],"Self-Attention":[61],"Network":[62],"(Ego-STAN),":[63],"which":[64,91],"uses":[65],"2D":[66,158],"image":[67],"representations":[68],"attention":[71],"both":[74],"distortions":[75],"in":[78,103,133],"ego-HPE.":[79],"Additionally,":[80],"introduce":[82],"spatial":[84],"concept":[85],"called":[86],"feature":[87],"map":[88],"tokens":[89],"(FMT)":[90],"endows":[92],"Ego-STAN":[93],"with":[94,162],"ability":[96],"draw":[98],"complex":[99],"encoded":[102],"videos.":[105],"Our":[106,166],"quantitative":[107],"evaluation":[108],"on":[109,118,157],"contemporary":[111],"xR-EgoPose":[112],"dataset,":[113],"achieves":[114],"38.2%":[116],"improvement":[117,156],"highest":[120],"error":[121],"joints":[122],"against":[123],"SOTA":[125],"model,":[127],"while":[128],"accomplishing":[129],"22%":[131],"decrease":[132],"number":[135],"parameters.":[137],"Finally,":[138],"also":[140,169],"demonstrate":[141],"generalization":[143],"capabilities":[144],"our":[146],"real-world":[149],"HPE":[150],"tasks":[151],"beyond":[152],"ego-views":[153],"achieving":[154],"7.7%":[155],"Human3.6M":[164],"dataset.":[165],"code":[167],"made":[170],"available":[171],"at:":[172],"https://github.com/jmpark0808/Ego-STAN":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}