{"id":"https://openalex.org/W7138194545","doi":"https://doi.org/10.1609/aaai.v40i5.37410","title":"SAME: Spatial-Aware Multimodal Egocentric Human Pose Estimation","display_name":"SAME: Spatial-Aware Multimodal Egocentric Human Pose Estimation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138194545","doi":"https://doi.org/10.1609/aaai.v40i5.37410"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37410","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37410","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37410/41372","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37410/41372","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129645238","display_name":"Yurong Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurong Fu","raw_affiliation_strings":["PICO\nTsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PICO\nTsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669392","display_name":"Peng Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153530","display_name":"Policy Innovation and Co-ordination Office","ror":"https://ror.org/052p8vb75","country_code":"HK","type":"government","lineage":["https://openalex.org/I2800550174","https://openalex.org/I4210153530"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Dai","raw_affiliation_strings":["PICO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PICO","institution_ids":["https://openalex.org/I4210153530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129737050","display_name":"Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153530","display_name":"Policy Innovation and Co-ordination Office","ror":"https://ror.org/052p8vb75","country_code":"HK","type":"government","lineage":["https://openalex.org/I2800550174","https://openalex.org/I4210153530"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["PICO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PICO","institution_ids":["https://openalex.org/I4210153530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129674945","display_name":"Feng Yiqiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153530","display_name":"Policy Innovation and Co-ordination Office","ror":"https://ror.org/052p8vb75","country_code":"HK","type":"government","lineage":["https://openalex.org/I2800550174","https://openalex.org/I4210153530"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Feng Yiqiang","raw_affiliation_strings":["PICO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PICO","institution_ids":["https://openalex.org/I4210153530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659230","display_name":"Yang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153530","display_name":"Policy Innovation and Co-ordination Office","ror":"https://ror.org/052p8vb75","country_code":"HK","type":"government","lineage":["https://openalex.org/I2800550174","https://openalex.org/I4210153530"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["PICO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PICO","institution_ids":["https://openalex.org/I4210153530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129653360","display_name":"Haoqian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"4067","last_page":"4075"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9463000297546387,"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":0.9463000297546387,"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/T12290","display_name":"Human Motion and Animation","score":0.008700000122189522,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.006000000052154064,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6866999864578247},{"id":"https://openalex.org/keywords/inertial-measurement-unit","display_name":"Inertial measurement unit","score":0.4666999876499176},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.46560001373291016},{"id":"https://openalex.org/keywords/simultaneous-localization-and-mapping","display_name":"Simultaneous localization and mapping","score":0.44760000705718994},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.3871000111103058},{"id":"https://openalex.org/keywords/inertial-frame-of-reference","display_name":"Inertial frame of reference","score":0.3580999970436096},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.35580000281333923},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.3346000015735626},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8119000196456909},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7888000011444092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426000237464905},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6866999864578247},{"id":"https://openalex.org/C79061980","wikidata":"https://www.wikidata.org/wiki/Q941680","display_name":"Inertial measurement unit","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C86369673","wikidata":"https://www.wikidata.org/wiki/Q1203659","display_name":"Simultaneous localization and mapping","level":4,"score":0.44760000705718994},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C173386949","wikidata":"https://www.wikidata.org/wiki/Q192735","display_name":"Inertial frame of reference","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.35580000281333923},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.3346000015735626},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C185078393","wikidata":"https://www.wikidata.org/wiki/Q313783","display_name":"Stereo camera","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C35861506","wikidata":"https://www.wikidata.org/wiki/Q17141434","display_name":"Stereo cameras","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2987632653","wikidata":"https://www.wikidata.org/wiki/Q7611220","display_name":"Stereo image","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C31451488","wikidata":"https://www.wikidata.org/wiki/Q5157586","display_name":"Computer stereo vision","level":3,"score":0.2639000117778778}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37410","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37410","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37410/41372","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37410","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37410","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37410","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37410/41372","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138194545.pdf","grobid_xml":"https://content.openalex.org/works/W7138194545.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Egocentric":[0],"human":[1],"pose":[2,197],"estimation":[3,198],"(HPE)":[4],"plays":[5],"a":[6,43,68,73,148,164,172],"crucial":[7],"role":[8],"in":[9,113],"immersive":[10],"applications":[11],"such":[12],"as":[13],"virtual":[14],"and":[15,57,62,86,102,143,156,171,178],"augmented":[16],"reality.":[17],"However,":[18],"existing":[19],"methods":[20],"relying":[21],"on":[22,72,191],"either":[23],"visual":[24],"or":[25,34],"sparse":[26,58],"inertial":[27],"data":[28],"alone":[29],"often":[30],"suffer":[31],"from":[32,53],"occlusion":[33],"ill-posed":[35],"problems.":[36],"In":[37,89,117],"this":[38],"work,":[39],"we":[40,162],"propose":[41],"SAME,":[42],"novel":[44],"spatial-aware":[45,166],"multimodal":[46],"fusion":[47],"framework":[48],"combining":[49],"the":[50,54,79,83,87,90,93,99,106,114,118,121,127,131,137,192],"complementary":[51],"signals":[52,95],"stereo":[55,84,107,168],"images":[56,108],"IMUs":[59],"for":[60,109,176],"accurate":[61],"robust":[63],"egocentric":[64,196],"HPE.":[65],"It":[66],"adopts":[67],"two-stage":[69],"network":[70,170],"based":[71],"dual":[74],"coordinate":[75,80],"frame":[76,101,129],"to":[77,153],"mitigate":[78],"inconsistencies":[81],"among":[82,159],"cameras":[85],"IMUs.":[88],"first":[91],"stage,":[92,120],"IMU":[94],"are":[96,124],"transformed":[97,125],"into":[98,126],"local":[100,115,122],"iteratively":[103],"fused":[104],"with":[105,130],"estimating":[110],"3D":[111],"poses":[112,123,134],"frame.":[116],"second":[119],"global":[128],"6DOF":[132],"head":[133],"provided":[135],"by":[136],"head-mounted":[138],"display's":[139],"(HMD)":[140],"SLAM":[141],"algorithm":[142],"then":[144],"temporally":[145],"aggregated":[146],"via":[147],"temporal":[149],"Transformer":[150,174],"network.":[151],"Meanwhile,":[152],"achieve":[154],"geometric":[155],"semantic":[157],"alignment":[158],"multi-modal":[160,195],"features,":[161],"present":[163],"depth-guided":[165],"deformable":[167],"attention":[169],"modality-aware":[173],"decoder":[175],"cross-view":[177],"cross-modal":[179],"feature":[180],"fusion.":[181],"Extensive":[182],"experiments":[183],"demonstrate":[184],"that":[185],"our":[186],"approach":[187],"achieves":[188],"state-of-the-art":[189],"performance":[190],"public":[193],"EMHI":[194],"benchmark.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2026-03-18T00:00:00"}