{"id":"https://openalex.org/W3094846751","doi":"https://doi.org/10.1145/3394171.3413651","title":"Adaptive Wasserstein Hourglass for Weakly Supervised RGB 3D Hand Pose Estimation","display_name":"Adaptive Wasserstein Hourglass for Weakly Supervised RGB 3D Hand Pose Estimation","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3094846751","doi":"https://doi.org/10.1145/3394171.3413651","mag":"3094846751"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5100718164","display_name":"Yumeng Zhang","orcid":"https://orcid.org/0000-0002-6444-292X"},"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":true,"raw_author_name":"Yumeng Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379176","display_name":"Li Chen","orcid":"https://orcid.org/0000-0001-7836-4849"},"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":"Li Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376625","display_name":"Yufeng Liu","orcid":"https://orcid.org/0000-0003-0848-5113"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Liu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035367145","display_name":"Wen Zheng","orcid":"https://orcid.org/0000-0002-6570-6245"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zheng","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080894318","display_name":"Jun\u2010Hai Yong","orcid":"https://orcid.org/0000-0002-4326-4167"},"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":"Junhai Yong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100718164"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6839,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72360019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2076","last_page":"2084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9868000149726868,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9807000160217285,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hourglass","display_name":"Hourglass","score":0.8741018176078796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7588329315185547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549216747283936},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.673876941204071},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5800925493240356},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5383284091949463},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.530229389667511},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5145267844200134},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5059711337089539},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5041593313217163},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5006067752838135},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5003743171691895},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4690423905849457},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4472603499889374},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.42503368854522705},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39280417561531067},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38286563754081726},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22472050786018372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17218923568725586}],"concepts":[{"id":"https://openalex.org/C127532173","wikidata":"https://www.wikidata.org/wiki/Q179904","display_name":"Hourglass","level":2,"score":0.8741018176078796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7588329315185547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549216747283936},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.673876941204071},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5800925493240356},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5383284091949463},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.530229389667511},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5145267844200134},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5059711337089539},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5041593313217163},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5006067752838135},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5003743171691895},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4690423905849457},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4472603499889374},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.42503368854522705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39280417561531067},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38286563754081726},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22472050786018372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17218923568725586},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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":26,"referenced_works":["https://openalex.org/W1928739709","https://openalex.org/W1990947293","https://openalex.org/W2100642335","https://openalex.org/W2104094955","https://openalex.org/W2187089797","https://openalex.org/W2307770531","https://openalex.org/W2593768305","https://openalex.org/W2756050327","https://openalex.org/W2774831247","https://openalex.org/W2795089319","https://openalex.org/W2795889831","https://openalex.org/W2798581336","https://openalex.org/W2892644985","https://openalex.org/W2897765997","https://openalex.org/W2949117887","https://openalex.org/W2962723986","https://openalex.org/W2962811204","https://openalex.org/W2962879692","https://openalex.org/W2962956488","https://openalex.org/W2963119249","https://openalex.org/W2963234092","https://openalex.org/W2964093990","https://openalex.org/W2979577579","https://openalex.org/W2980096013","https://openalex.org/W2998115938","https://openalex.org/W3034203264"],"related_works":["https://openalex.org/W3139354174","https://openalex.org/W4379932926","https://openalex.org/W3209856089","https://openalex.org/W4253893311","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4287600488","https://openalex.org/W4312694060","https://openalex.org/W4307623796"],"abstract_inverted_index":{"The":[0],"deficiency":[1],"of":[2,8,26,57,111],"labeled":[3],"training":[4],"data":[5],"is":[6],"one":[7],"the":[9,39,49,52,82,101,105,112,122,128,134,146,151],"bottlenecks":[10],"in":[11,55,136,168],"3D":[12,76,180],"hand":[13,77,109],"pose":[14,78,181],"estimation":[15,79,182],"from":[16],"monocular":[17],"RGB":[18],"images.":[19],"Synthetic":[20],"datasets":[21,37,89,162],"have":[22,44],"a":[23,66,95],"large":[24,59,83],"number":[25],"images":[27],"with":[28,35,178],"precise":[29],"annotations,":[30],"but":[31],"their":[32,58],"obvious":[33],"difference":[34],"real-world":[36,88],"limits":[38],"generalization":[40],"ability.":[41],"Few":[42],"efforts":[43],"been":[45],"made":[46],"to":[47,80,99],"bridge":[48],"gap":[50,84,153],"between":[51,85,154],"two":[53,113,155,160],"domains":[54],"terms":[56],"differences.":[60,129],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"domain":[67,185],"adaptation":[68,186],"method":[69,166],"called":[70],"Adaptive":[71,91],"Wasserstein":[72,92],"Hourglass":[73,93],"for":[74],"weakly-supervised":[75],"close":[81,119],"synthetic":[86],"and":[87,103,172,184],"flexibly.":[90],"utilizes":[94],"feature":[96],"similarity":[97],"metric":[98],"identify":[100],"differences":[102],"explore":[104],"common":[106,131],"features":[107,116,126,132,144,171],"(e.g.,":[108],"structure)":[110],"datasets.":[114],"Common":[115],"are":[117],"drawn":[118],"adaptively":[120],"during":[121],"training,":[123],"whereas":[124,141],"domain-specific":[125,143],"retain":[127],"Learning":[130],"helps":[133],"network":[135],"focusing":[137],"on":[138,159],"pose-related":[139],"information,":[140],"maintaining":[142],"reduces":[145],"optimization":[147],"difficulty":[148],"when":[149,176],"closing":[150],"big":[152],"domains.":[156],"Extensive":[157],"evaluations":[158],"benchmark":[161],"demonstrate":[163],"that":[164],"our":[165],"succeeds":[167],"distinguishing":[169],"different":[170],"achieves":[173],"optimal":[174],"results":[175],"compared":[177],"state-of-the-art":[179],"approaches":[183],"methods.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}