{"id":"https://openalex.org/W4403791598","doi":"https://doi.org/10.1145/3664647.3681265","title":"Geometry-Guided Diffusion Model with Masked Transformer for Robust Multi-View 3D Human Pose Estimation","display_name":"Geometry-Guided Diffusion Model with Masked Transformer for Robust Multi-View 3D Human Pose Estimation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791598","doi":"https://doi.org/10.1145/3664647.3681265"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681265","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681265","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085962194","display_name":"X. Zhang","orcid":"https://orcid.org/0009-0000-9915-5608"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyi Zhang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113000500","display_name":"Qinpeng Cui","orcid":"https://orcid.org/0009-0008-6796-2112"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinpeng Cui","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020418509","display_name":"Qiqi Bao","orcid":"https://orcid.org/0000-0001-9599-1844"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiqi Bao","raw_affiliation_strings":["Zhejiang University of Science & Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Science & Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026184280","display_name":"Wenming Yang","orcid":"https://orcid.org/0000-0002-2506-1286"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Yang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009239895","display_name":"Qingmin Liao","orcid":"https://orcid.org/0000-0002-7509-3964"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingmin Liao","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085962194"],"corresponding_institution_ids":["https://openalex.org/I4210114105"],"apc_list":null,"apc_paid":null,"fwci":0.5499,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67237142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9958000183105469,"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":0.5811392068862915},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5370510816574097},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.53394615650177},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4224853515625},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.4217658042907715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4197880029678345},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15637996792793274},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11531838774681091},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0657913088798523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5811392068862915},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5370510816574097},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.53394615650177},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4224853515625},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.4217658042907715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4197880029678345},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15637996792793274},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11531838774681091},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0657913088798523}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681265","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681265","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W190293641","https://openalex.org/W1530404542","https://openalex.org/W2200124539","https://openalex.org/W2963335855","https://openalex.org/W2963402313","https://openalex.org/W2963873475","https://openalex.org/W2964221239","https://openalex.org/W2984313141","https://openalex.org/W3009246422","https://openalex.org/W3034971010","https://openalex.org/W3035068106","https://openalex.org/W3094016061","https://openalex.org/W3094830752","https://openalex.org/W3104343368","https://openalex.org/W3173873424","https://openalex.org/W3201519611","https://openalex.org/W3203617912","https://openalex.org/W4200420145","https://openalex.org/W4225557002","https://openalex.org/W4283825932","https://openalex.org/W4292829105","https://openalex.org/W4312417903","https://openalex.org/W4312721455","https://openalex.org/W4313068951","https://openalex.org/W4379985979","https://openalex.org/W4385271020","https://openalex.org/W4385968244","https://openalex.org/W4386075813","https://openalex.org/W4386083132","https://openalex.org/W4387968000","https://openalex.org/W4387969079","https://openalex.org/W4388186997","https://openalex.org/W4389298891","https://openalex.org/W4390872990","https://openalex.org/W4390873435","https://openalex.org/W4390874574"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"Recent":[0],"research":[1],"on":[2,136],"Diffusion":[3],"Models":[4],"and":[5,29,75,149,161,181],"Transformers":[6],"has":[7],"brought":[8],"significant":[9],"advancements":[10],"to":[11,22,65,109,124,175],"3D":[12,49,68],"Human":[13],"Pose":[14],"Estimation":[15],"(HPE).":[16],"Nonetheless,":[17],"existing":[18],"methods":[19,157],"often":[20],"fail":[21],"concurrently":[23],"address":[24,79],"the":[25,52,55,67,80,106,111,114,121],"issues":[26],"of":[27,54,83,113],"accuracy":[28,112,148],"generalization.":[30,150],"In":[31,169],"this":[32],"paper,":[33],"we":[34,86,101],"propose":[35],"a":[36,58,88,130,145],"Geometry-guided":[37],"Dif":[38],"fusion":[39],"Model":[40],"with":[41,165],"Masked":[42,141],"Transformer":[43],"(Masked":[44],"Gifformer)":[45],"for":[46],"robust":[47],"multi-view":[48,60],"HPE.":[50],"Within":[51],"framework":[53],"diffusion":[56,107],"model,":[57],"hierarchical":[59],"trans-former-based":[61],"denoiser":[62],"is":[63,117],"exploited":[64],"fit":[66],"pose":[69],"distribution":[70],"by":[71,119,158],"systematically":[72],"integrating":[73],"joint":[74],"view":[76],"information.":[77],"To":[78],"long-standing":[81],"problem":[82],"poor":[84],"generalization,":[85],"introduce":[87],"fully":[89],"random":[90],"mask":[91],"mechanism":[92],"without":[93],"any":[94],"additional":[95],"learnable":[96],"modules":[97],"or":[98],"parameters.":[99],"Furthermore,":[100],"incorporate":[102],"geometric":[103],"guidance":[104,132],"into":[105],"model":[108],"enhance":[110],"model.":[115],"This":[116],"achieved":[118],"optimizing":[120],"sampling":[122],"process":[123],"minimize":[125],"reprojection":[126],"errors":[127],"through":[128],"modeling":[129],"conditional":[131],"distribution.":[133],"Extensive":[134],"experiments":[135],"two":[137],"benchmarks":[138],"demonstrate":[139],"that":[140],"Gifformer":[142],"effectively":[143],"achieves":[144,162],"trade-off":[146],"between":[147],"Specifically,":[151],"our":[152,171],"method":[153,172],"outperforms":[154],"other":[155],"probabilistic":[156],">":[159],"40%":[160],"comparable":[163],"results":[164],"state-of-the-art":[166],"deterministic":[167],"methods.":[168],"addition,":[170],"exhibits":[173],"robustness":[174],"varying":[176],"camera":[177],"numbers,":[178],"spatial":[179],"arrangements,":[180],"datasets.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}