{"id":"https://openalex.org/W4402979294","doi":"https://doi.org/10.1109/icme57554.2024.10687919","title":"Diffusion based Coarse-to-Fine Network for 3D Human Pose and Shape Estimation from monocular video","display_name":"Diffusion based Coarse-to-Fine Network for 3D Human Pose and Shape Estimation from monocular video","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979294","doi":"https://doi.org/10.1109/icme57554.2024.10687919"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5112378612","display_name":"Chuqiao Wu","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":"Chuqiao Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103111976","display_name":"Haitao Huang","orcid":"https://orcid.org/0009-0003-3881-3162"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Huang","raw_affiliation_strings":["Fudan University,Department of Electronic Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110649314","display_name":"Wenming Yang","orcid":"https://orcid.org/0000-0003-1425-8013"},"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":"Wenming Yang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.075,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87230091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12994","display_name":"Infrared Thermography in Medicine","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12994","display_name":"Infrared Thermography in Medicine","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9840999841690063,"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":0.9815000295639038,"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/monocular","display_name":"Monocular","score":0.7743757963180542},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7383195161819458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6609105467796326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6553943753242493},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6448021531105042},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6318716406822205},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.41814783215522766},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3576262593269348},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06941455602645874}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7743757963180542},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7383195161819458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6609105467796326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6553943753242493},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6448021531105042},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6318716406822205},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.41814783215522766},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3576262593269348},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06941455602645874},{"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/icme57554.2024.10687919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2101032778","https://openalex.org/W2752782242","https://openalex.org/W2797184202","https://openalex.org/W2895748257","https://openalex.org/W2916798096","https://openalex.org/W2964084369","https://openalex.org/W2964318832","https://openalex.org/W2975420824","https://openalex.org/W2981637078","https://openalex.org/W3035551320","https://openalex.org/W3096831136","https://openalex.org/W3110022498","https://openalex.org/W3155072588","https://openalex.org/W3174980830","https://openalex.org/W3212516020","https://openalex.org/W4214619583","https://openalex.org/W4214770715","https://openalex.org/W4221142859","https://openalex.org/W4312518484","https://openalex.org/W4312874524","https://openalex.org/W4385245566","https://openalex.org/W4386076655","https://openalex.org/W4390874241"],"related_works":["https://openalex.org/W4253893311","https://openalex.org/W3089306886","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4393563475","https://openalex.org/W4307623796","https://openalex.org/W4394784820"],"abstract_inverted_index":{"Video-based":[0],"3D":[1],"human":[2,13,78,106],"pose":[3,25,43,97],"and":[4,26,40,108,137],"shape":[5,27],"estimation":[6],"plays":[7],"a":[8,20,62,85,118],"crucial":[9],"role":[10],"in":[11,53],"enhancing":[12],"understanding.":[14],"However,":[15],"existing":[16],"methods":[17,131],"typically":[18],"employ":[19],"unified":[21],"model":[22,109],"for":[23],"both":[24],"parameter":[28],"estimation,":[29],"neglecting":[30],"the":[31,82,103,114,121],"inherent":[32],"uncertainty":[33],"introduced":[34],"by":[35],"factors":[36],"such":[37],"as":[38,117],"blurring":[39],"occlusion":[41],"during":[42],"estimation.":[44],"This":[45],"oversight":[46],"can":[47],"lead":[48],"to":[49,76,94,101],"suboptimal":[50],"solutions,":[51],"especially":[52],"challenging":[54],"scenarios.":[55],"To":[56],"tackle":[57],"this":[58],"issue,":[59],"we":[60,112],"propose":[61],"Coarse-to-Fine":[63],"Diffusion-based":[64],"Refinement":[65],"Network":[66],"(DR-Net).":[67],"The":[68],"initial":[69],"regressor":[70,88],"undergoes":[71],"pre-training":[72],"on":[73,132],"large":[74],"datasets":[75,134],"comprehend":[77],"motion":[79,107],"dynamics.":[80],"In":[81,99],"refinement":[83,87],"framework,":[84],"diffusion-based":[86,122],"is":[89],"introduced,":[90],"utilizing":[91],"reverse":[92],"denoising":[93],"incrementally":[95],"refine":[96],"parameters.":[98],"order":[100],"capture":[102],"kinematics":[104],"of":[105],"parameter-feature":[110],"relationships,":[111],"design":[113],"GCN-ATT":[115],"module":[116],"denoiser":[119],"within":[120],"regressor.":[123],"Extensive":[124],"experiments":[125],"demonstrate":[126],"its":[127],"superiority":[128],"over":[129],"state-of-the-art":[130],"benchmark":[133],"Human3.6M":[135],"[1]":[136],"3DPW":[138],"[2].":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}