{"id":"https://openalex.org/W3009850394","doi":"https://doi.org/10.1109/wacv45572.2020.9093316","title":"3D Hand Pose Estimation with Disentangled Cross-Modal Latent Space","display_name":"3D Hand Pose Estimation with Disentangled Cross-Modal Latent Space","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3009850394","doi":"https://doi.org/10.1109/wacv45572.2020.9093316","mag":"3009850394"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-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/A5102031963","display_name":"Jiajun Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jiajun Gu","raw_affiliation_strings":["The University of Sydney"],"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443935","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0002-8043-0312"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["The University of Sydney"],"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["The University of Sydney"],"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057762021","display_name":"Weichen Zhang","orcid":"https://orcid.org/0000-0003-2929-0921"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weichen Zhang","raw_affiliation_strings":["The University of Sydney"],"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101517522","display_name":"Jiafeng Li","orcid":"https://orcid.org/0000-0001-6976-7275"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Li","raw_affiliation_strings":["Beijing University of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448036","display_name":"Zhuo Li","orcid":"https://orcid.org/0000-0002-9937-2669"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhuo","raw_affiliation_strings":["Beijing University of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102031963"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.2701,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.82007461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"380","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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":0.9991999864578247,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9785000085830688,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7209488153457642},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6577801704406738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6551423072814941},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6035211086273193},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5125510692596436},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5084801912307739},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5032035708427429},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4963715672492981},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4521957337856293},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4311525821685791},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4223829507827759},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41018742322921753},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36260348558425903}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7209488153457642},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6577801704406738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6551423072814941},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6035211086273193},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5125510692596436},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5084801912307739},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5032035708427429},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4963715672492981},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4521957337856293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4311525821685791},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4223829507827759},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41018742322921753},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36260348558425903},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1928739709","https://openalex.org/W1959608418","https://openalex.org/W2075156252","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2161604086","https://openalex.org/W2162254475","https://openalex.org/W2166665167","https://openalex.org/W2194775991","https://openalex.org/W2218414108","https://openalex.org/W2413439537","https://openalex.org/W2546190447","https://openalex.org/W2546353648","https://openalex.org/W2796453247","https://openalex.org/W2797784912","https://openalex.org/W2798434327","https://openalex.org/W2798581336","https://openalex.org/W2798681837","https://openalex.org/W2798895895","https://openalex.org/W2799191197","https://openalex.org/W2883997473","https://openalex.org/W2892644985","https://openalex.org/W2897765997","https://openalex.org/W2951006673","https://openalex.org/W2962793481","https://openalex.org/W2962811204","https://openalex.org/W2962926199","https://openalex.org/W2962947361","https://openalex.org/W2963073614","https://openalex.org/W2963207848","https://openalex.org/W2963226019","https://openalex.org/W2963377353","https://openalex.org/W2963508807","https://openalex.org/W2963577185","https://openalex.org/W2963859396","https://openalex.org/W2963950354","https://openalex.org/W2964304707","https://openalex.org/W2979577579","https://openalex.org/W2982601397","https://openalex.org/W2984624776","https://openalex.org/W2987087879","https://openalex.org/W2998351473","https://openalex.org/W3159890710","https://openalex.org/W4320013936","https://openalex.org/W6640963894","https://openalex.org/W6678815747","https://openalex.org/W6718140377","https://openalex.org/W6729320488","https://openalex.org/W6734074887","https://openalex.org/W6746154080","https://openalex.org/W6753249163","https://openalex.org/W6754583656","https://openalex.org/W6756070714","https://openalex.org/W6795104053"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W2988134182","https://openalex.org/W2770818364"],"abstract_inverted_index":{"Estimating":[0],"3D":[1,31,51,61,107,217],"hand":[2,36,108,137,149,218],"pose":[3,109,150,219],"from":[4,143],"a":[5,10,40,64,162,177],"single":[6,214],"RGB":[7,35,48,58,144],"image":[8,37,49,215],"is":[9,68,205],"challenging":[11],"task":[12],"because":[13],"of":[14,33,78,121],"its":[15],"ill-posed":[16],"nature":[17],"(i.e.,":[18,47,57],"depth":[19],"ambiguity).":[20],"Recently,":[21],"various":[22],"generative":[23],"approaches":[24],"have":[25],"been":[26],"proposed":[27,112,202],"to":[28,89,134,145,180,183,207],"predict":[29],"the":[30,71,76,79,91,131,148,157,171,184,210],"joints":[32],"an":[34,166],"by":[38,160],"learning":[39,77,168],"unified":[41,65],"latent":[42,66,81,92,100,104,151,173],"space":[43,67,93,101,105],"between":[44],"two":[45,95,122,132,158,190],"modalities":[46,159],"and":[50,60,102,126,139,197],"joints).":[52],"However,":[53],"projecting":[54],"multi-modal":[55],"data":[56],"images":[59],"joints)":[62],"into":[63,94],"difficult":[69],"as":[70],"modality-specific":[72,141],"features":[73],"usually":[74],"interfere":[75],"optimal":[80],"space.":[82],"Hence":[83],"in":[84],"this":[85],"paper,":[86],"we":[87,153,175],"propose":[88],"disentangle":[90],"sub-latent":[96],"spaces:":[97],"modality-":[98],"specific":[99],"pose-specific":[103],"for":[106],"estimation.":[110,220],"Our":[111],"method,":[113],"namely":[114],"Disentangled":[115],"Cross-Modal":[116],"Latent":[117],"Space":[118],"(DCMLS),":[119],"consists":[120],"variational":[123],"autoencoder":[124],"networks":[125],"auxiliary":[127],"components":[128],"which":[129],"connect":[130],"VAEs":[133],"align":[135,154],"underlying":[136],"poses":[138],"transfer":[140],"context":[142,172,178],"3D.":[146],"For":[147,170],"space,":[152,174],"it":[155],"with":[156,165],"using":[161],"cross-modal":[163,185],"discriminator":[164],"adversarial":[167],"strategy.":[169],"learn":[176],"translator":[179],"gain":[181],"access":[182],"context.":[186],"Experimental":[187],"results":[188],"on":[189,213],"widely":[191],"used":[192],"public":[193],"benchmark":[194],"datasets":[195],"RHD":[196],"STB":[198],"demonstrate":[199],"that":[200],"our":[201],"DCMLS":[203],"method":[204],"able":[206],"clearly":[208],"outperform":[209],"state-of-the-art":[211],"ones":[212],"based":[216]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}