{"id":"https://openalex.org/W4399727767","doi":"https://doi.org/10.1109/tcsvt.2024.3415348","title":"Diffusion-Based Hypotheses Generation and Joint-Level Hypotheses Aggregation for 3D Human Pose Estimation","display_name":"Diffusion-Based Hypotheses Generation and Joint-Level Hypotheses Aggregation for 3D Human Pose Estimation","publication_year":2024,"publication_date":"2024-06-17","ids":{"openalex":"https://openalex.org/W4399727767","doi":"https://doi.org/10.1109/tcsvt.2024.3415348"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3415348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3415348","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/A5038108567","display_name":"Wenkang Shan","orcid":"https://orcid.org/0009-0000-3038-6432"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenkang Shan","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080183678","display_name":"Yuhuai Zhang","orcid":"https://orcid.org/0000-0002-8861-0510"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhuai Zhang","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055937409","display_name":"Xinfeng Zhang","orcid":"https://orcid.org/0000-0002-7517-3868"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfeng Zhang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385183","display_name":"Shanshe Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshe Wang","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038791429","display_name":"Xilong Zhou","orcid":"https://orcid.org/0000-0002-4133-8783"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilong Zhou","raw_affiliation_strings":["Lenovo (Beijing) Company Ltd., Beijing, China","Lenovo (Beijing) Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Lenovo (Beijing) Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"Lenovo (Beijing) Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Ma","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018478553","display_name":"Wen Gao","orcid":"https://orcid.org/0000-0002-8070-802X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Gao","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5038108567"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.2249,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79843977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"34","issue":"11","first_page":"10678","last_page":"10691"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.5950543880462646},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5478774905204773},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.542073667049408},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5280985236167908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41247445344924927},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34508395195007324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09615814685821533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5950543880462646},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5478774905204773},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.542073667049408},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5280985236167908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41247445344924927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34508395195007324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09615814685821533},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3415348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3415348","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":[],"awards":[{"id":"https://openalex.org/G1316932678","display_name":null,"funder_award_id":"62071449","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3887166938","display_name":null,"funder_award_id":"U21B2012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7903788244","display_name":null,"funder_award_id":"62025101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8505359809","display_name":null,"funder_award_id":"U20A20184","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8573909329","display_name":null,"funder_award_id":"E2ET1104","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1496462336","https://openalex.org/W2088196373","https://openalex.org/W2099333815","https://openalex.org/W2101032778","https://openalex.org/W2617321867","https://openalex.org/W2797184202","https://openalex.org/W2895748257","https://openalex.org/W2945556069","https://openalex.org/W2962711434","https://openalex.org/W2962896489","https://openalex.org/W2963150697","https://openalex.org/W2963225012","https://openalex.org/W2963781481","https://openalex.org/W2964221239","https://openalex.org/W2964291722","https://openalex.org/W2966735886","https://openalex.org/W2968459013","https://openalex.org/W2982627166","https://openalex.org/W3034448411","https://openalex.org/W3037982482","https://openalex.org/W3039961680","https://openalex.org/W3096831136","https://openalex.org/W3106838237","https://openalex.org/W3106882556","https://openalex.org/W3126541466","https://openalex.org/W3136525061","https://openalex.org/W3155072588","https://openalex.org/W3183950642","https://openalex.org/W3200418030","https://openalex.org/W3203617912","https://openalex.org/W3205327953","https://openalex.org/W3216352822","https://openalex.org/W4225557002","https://openalex.org/W4304083983","https://openalex.org/W4312249545","https://openalex.org/W4312417903","https://openalex.org/W4312797994","https://openalex.org/W4312851679","https://openalex.org/W4312966446","https://openalex.org/W4313130756","https://openalex.org/W4366748084","https://openalex.org/W4366966749","https://openalex.org/W4377717242","https://openalex.org/W4379033842","https://openalex.org/W4380905910","https://openalex.org/W4381946531","https://openalex.org/W4385245566","https://openalex.org/W4386075813","https://openalex.org/W4386076485","https://openalex.org/W4387805784","https://openalex.org/W4388192390","https://openalex.org/W4390873166","https://openalex.org/W4390873651","https://openalex.org/W4390874574","https://openalex.org/W6610566761","https://openalex.org/W6679045638","https://openalex.org/W6687045409","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6779823529","https://openalex.org/W6782095612","https://openalex.org/W6783713337","https://openalex.org/W6846258481","https://openalex.org/W6846598164","https://openalex.org/W6846961251","https://openalex.org/W6847561146"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"To":[0],"combine":[1],"the":[2,75,80,99,133,158,164,169,178,181,186,195,209,232,236],"advantages":[3],"of":[4,43,216],"deterministic":[5,90,238],"and":[6,22,94,104,124,162,176,212,239],"probabilistic":[7,240],"3D":[8,33,45,62,82,91,146,154],"human":[9],"pose":[10,15,46,92,105,147,155],"estimation":[11,16],"methods,":[12],"we":[13,28,114],"decompose":[14],"into":[17,143,194],"two":[18,108,116,228],"processes:":[19],"hypotheses":[20,23,26,47,112,139,156],"generation":[21,35],"aggregation.":[24],"For":[25,111],"generation,":[27],"propose":[29,115],"a":[30,40,49,55,65,70,119,125,144,202],"novel":[31],"Diffusion-based":[32],"Pose":[34],"(D3DP)":[36],"method.":[37],"D3DP":[38,85,142],"generates":[39],"diversified":[41],"group":[42],"plausible":[44],"from":[48],"single":[50,145],"2D":[51,159,210],"keypoint":[52],"observation.":[53],"Utilizing":[54],"diffusion":[56],"process,":[57],"it":[58],"gradually":[59],"transforms":[60],"ground-truth":[61],"poses":[63],"towards":[64],"random":[66],"distribution,":[67],"subsequently":[68],"employing":[69],"conditioned":[71],"denoiser":[72],"guided":[73],"by":[74,141,221],"observed":[76],"keypoints":[77],"to":[78,97,136,157],"recover":[79],"uncorrupted":[81],"poses.":[83],"Moreover,":[84],"is":[86],"compatible":[87],"with":[88,180],"existing":[89],"estimators":[93],"allows":[95],"users":[96],"optimize":[98],"trade-off":[100],"between":[101],"computational":[102],"efficiency":[103],"accuracy":[106],"via":[107],"adjustable":[109],"parameters.":[110],"aggregation,":[113],"alternative":[117],"approaches:":[118],"Reprojection-Based":[120],"Selection":[121,127],"(RBS)":[122],"method":[123,234],"Hypotheses":[126],"Network":[128],"(HSN).":[129],"These":[130],"methods":[131,200],"adopt":[132],"joint-level":[134],"strategy":[135,205],"assemble":[137],"multiple":[138],"generated":[140],"for":[148],"practical":[149],"use.":[150],"Specifically,":[151],"RBS":[152],"reprojects":[153],"camera":[160],"plane,":[161],"selects":[163,177],"best":[165],"hypothesis":[166,175,179],"based":[167],"on":[168,208,227],"reprojection":[170],"errors.":[171],"HSN":[172],"evaluates":[173],"each":[174],"highest":[182],"confidence":[183],"score":[184],"as":[185],"output.":[187],"Then":[188],"these":[189],"selected":[190],"joints":[191],"are":[192],"combined":[193],"final":[196],"pose.":[197],"The":[198],"proposed":[199,233],"implement":[201],"joint-by-joint":[203],"aggregation":[204],"that":[206,231],"capitalizes":[207],"prior":[211],"temporal":[213],"information,":[214],"both":[215],"which":[217],"have":[218],"been":[219],"ignored":[220],"previous":[222],"pose-level":[223],"methods.":[224],"Extensive":[225],"experiments":[226],"benchmarks":[229],"highlight":[230],"outperforms":[235],"state-of-the-art":[237],"approaches.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}