{"id":"https://openalex.org/W4285069978","doi":"https://doi.org/10.1109/tcsvt.2023.3244152","title":"Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet","display_name":"Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4285069978","doi":"https://doi.org/10.1109/tcsvt.2023.3244152"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3244152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3244152","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5077144356","display_name":"Shihao Zou","orcid":"https://orcid.org/0000-0002-9042-6069"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","US"],"is_corresponding":true,"raw_author_name":"Shihao Zou","raw_affiliation_strings":["Meta Reality Labs, Redmond, WA, USA","Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005665145","display_name":"Yuanlu Xu","orcid":"https://orcid.org/0000-0002-7095-1018"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanlu Xu","raw_affiliation_strings":["Meta Reality Labs, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323228","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-8046-9110"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Meta Reality Labs, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110921670","display_name":"Lingni Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lingni Ma","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753413","display_name":"Li Cheng","orcid":"https://orcid.org/0000-0003-3261-3533"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Li Cheng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033491653","display_name":"Minh Vo","orcid":"https://orcid.org/0000-0002-5091-9010"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minh Vo","raw_affiliation_strings":["Meta Reality Labs, Redmond, WA, USA","Spree3D, Incline, NV, USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Spree3D, Incline, NV, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5077144356"],"corresponding_institution_ids":["https://openalex.org/I154425047","https://openalex.org/I4210128585"],"apc_list":null,"apc_paid":null,"fwci":2.2972,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90016084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":"9","first_page":"4921","last_page":"4933"},"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":0.9983000159263611,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8378621339797974},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.8282754421234131},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.7484029531478882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7080386877059937},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6238791942596436},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5034357905387878},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49622851610183716},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.49067509174346924},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4358904957771301},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3751143515110016},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.2249566912651062},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.11375540494918823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378621339797974},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8282754421234131},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.7484029531478882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7080386877059937},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6238791942596436},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5034357905387878},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49622851610183716},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.49067509174346924},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4358904957771301},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3751143515110016},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2249566912651062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.11375540494918823},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3244152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3244152","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G3949280154","display_name":null,"funder_award_id":"RGPIN-2019-04575","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320319946","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27"},{"id":"https://openalex.org/F4320325651","display_name":"Alberta Innovates","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2080873731","https://openalex.org/W2175012183","https://openalex.org/W2502226073","https://openalex.org/W2771965516","https://openalex.org/W2792747672","https://openalex.org/W2797515701","https://openalex.org/W2798411580","https://openalex.org/W2888934629","https://openalex.org/W2913824500","https://openalex.org/W2916798096","https://openalex.org/W2934361577","https://openalex.org/W2959975024","https://openalex.org/W2962701817","https://openalex.org/W2962711434","https://openalex.org/W2962730651","https://openalex.org/W2963001155","https://openalex.org/W2963402313","https://openalex.org/W2963669520","https://openalex.org/W2964084369","https://openalex.org/W2964185410","https://openalex.org/W2964221239","https://openalex.org/W2964238416","https://openalex.org/W2977426443","https://openalex.org/W2984349976","https://openalex.org/W2986352270","https://openalex.org/W2986760165","https://openalex.org/W2993728126","https://openalex.org/W2998273692","https://openalex.org/W3023681781","https://openalex.org/W3035129432","https://openalex.org/W3035278762","https://openalex.org/W3035435924","https://openalex.org/W3043157863","https://openalex.org/W3045471054","https://openalex.org/W3047772167","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3101560663","https://openalex.org/W3106126861","https://openalex.org/W3107944344","https://openalex.org/W3109597949","https://openalex.org/W3116592456","https://openalex.org/W3119686997","https://openalex.org/W3136525061","https://openalex.org/W3171516518","https://openalex.org/W3173811519","https://openalex.org/W3174042812","https://openalex.org/W3175199633","https://openalex.org/W3177383258","https://openalex.org/W3189677397","https://openalex.org/W3192939302","https://openalex.org/W3195349439","https://openalex.org/W3196703792","https://openalex.org/W4213207977","https://openalex.org/W4214619583","https://openalex.org/W4283382804","https://openalex.org/W4292692470","https://openalex.org/W4312249545","https://openalex.org/W4312473433","https://openalex.org/W4312562660","https://openalex.org/W4312925317","https://openalex.org/W4312967365","https://openalex.org/W4313161900","https://openalex.org/W4385245566","https://openalex.org/W6735992252","https://openalex.org/W6754577284","https://openalex.org/W6784094891","https://openalex.org/W6803696282"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W3036724449","https://openalex.org/W2798329462","https://openalex.org/W1511521437","https://openalex.org/W3201315194","https://openalex.org/W4318980730","https://openalex.org/W2950904665","https://openalex.org/W2985134635","https://openalex.org/W4289376745","https://openalex.org/W2896663616"],"abstract_inverted_index":{"Multi-person":[0],"pose":[1,10,19,84,135,139,143,150,182],"understanding":[2],"from":[3,108,127],"RGB":[4],"videos":[5],"involves":[6],"three":[7,69,169],"complex":[8],"tasks:":[9],"estimation,":[11,85,183],"tracking":[12,26],"and":[13,24,61,87,131,152,185],"motion":[14,32,88],"forecasting.":[15,33,186],"Intuitively,":[16],"accurate":[17],"multi-person":[18,82,138,149],"estimation":[20],"facilitates":[21],"robust":[22,25],"tracking,":[23,86,184],"builds":[27],"crucial":[28],"history":[29],"for":[30,137,181],"correct":[31],"Most":[34],"existing":[35],"works":[36],"either":[37],"focus":[38],"on":[39,168],"a":[40,77,92,117,156],"single":[41,93,157],"task":[42],"or":[43],"employ":[44],"multi-stage":[45],"approaches":[46],"to":[47,54,64,80,104,122,132,147],"solving":[48],"multiple":[49],"tasks":[50],"separately,":[51],"which":[52],"tends":[53],"make":[55],"sub-optimal":[56],"decision":[57],"at":[58,190],"each":[59],"stage":[60],"also":[62],"fail":[63],"exploit":[65],"correlations":[66],"among":[67],"the":[68,109,124,128,160,164],"tasks.":[70],"In":[71,159],"this":[72,114],"paper,":[73],"we":[74,162],"propose":[75,96],"Snipper,":[76],"unified":[78],"framework":[79],"perform":[81],"3D":[83],"forecasting":[89],"simultaneously":[90],"in":[91,155],"stage.":[94],"We":[95],"an":[97],"efficient":[98],"yet":[99],"powerful":[100],"deformable":[101,115],"attention":[102],"mechanism":[103],"aggregate":[105],"spatiotemporal":[106,125],"information":[107],"video":[110,118],"snippet.":[111],"Building":[112],"upon":[113],"attention,":[116],"transformer":[119],"is":[120,188],"learned":[121],"encode":[123],"features":[126,136],"multi-frame":[129],"snippet":[130],"decode":[133],"informative":[134],"queries.":[140],"Finally,":[141],"these":[142],"queries":[144],"are":[145],"regressed":[146],"predict":[148],"trajectories":[151],"future":[153],"motions":[154],"shot.":[158],"experiments,":[161],"show":[163],"effectiveness":[165],"of":[166],"Snipper":[167],"challenging":[170],"public":[171],"datasets":[172],"where":[173],"our":[174],"generic":[175],"model":[176],"rivals":[177],"specialized":[178],"state-of-art":[179],"baselines":[180],"Code":[187],"available":[189],"<uri":[191],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[192],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[193],"https://github.com/JimmyZou/Snipper</uri>":[194],".":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}