{"id":"https://openalex.org/W4416960674","doi":"https://doi.org/10.1109/tpami.2025.3632829","title":"Grid Convolution for 3D Human Pose Estimation","display_name":"Grid Convolution for 3D Human Pose Estimation","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416960674","doi":"https://doi.org/10.1109/tpami.2025.3632829","pmid":"https://pubmed.ncbi.nlm.nih.gov/41336162"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3632829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3632829","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5026821972","display_name":"Yangyuxuan Kang","orcid":"https://orcid.org/0009-0009-4597-0100"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yangyuxuan Kang","raw_affiliation_strings":["Intel Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongqi Cai","orcid":"https://orcid.org/0009-0000-8178-7287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongqi Cai","raw_affiliation_strings":["Intel Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuyang Liu","orcid":"https://orcid.org/0009-0007-1174-7045"},"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":"Yuyang Liu","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042982818","display_name":"Anbang Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anbang Yao","raw_affiliation_strings":["Intel Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087453468","display_name":"Shandong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shandong Wang","raw_affiliation_strings":["Intel Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yurong Chen","orcid":"https://orcid.org/0000-0001-9333-1746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yurong Chen","raw_affiliation_strings":["Intel Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103466668","display_name":"Enhua Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhua Wu","raw_affiliation_strings":["Key Laboratory of Systems Software (CAS) and SKLCS, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Systems Software (CAS) and SKLCS, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5026821972"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38467007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"2936","last_page":"2953"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9671000242233276,"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":0.9671000242233276,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.004600000102072954,"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/pose","display_name":"Pose","score":0.7544999718666077},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.7164000272750854},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6191999912261963},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.614300012588501},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5449000000953674},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.49149999022483826},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.474700003862381},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4745999872684479},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4611999988555908}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7544999718666077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7455000281333923},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.7164000272750854},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6191999912261963},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.614300012588501},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.474700003862381},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4611999988555908},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.42899999022483826},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C57077369","wikidata":"https://www.wikidata.org/wiki/Q7075747","display_name":"Occupancy grid mapping","level":4,"score":0.3504999876022339},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C126795593","wikidata":"https://www.wikidata.org/wiki/Q7333813","display_name":"Rigid transformation","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C193828747","wikidata":"https://www.wikidata.org/wiki/Q864118","display_name":"Binary image","level":4,"score":0.25429999828338623}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011187","descriptor_name":"Posture","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D011187","descriptor_name":"Posture","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3632829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3632829","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41336162","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41336162","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6479462796","display_name":null,"funder_award_id":"62332015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2080873731","https://openalex.org/W2087681821","https://openalex.org/W2101032778","https://openalex.org/W2135533529","https://openalex.org/W2604375920","https://openalex.org/W2605947573","https://openalex.org/W2605973302","https://openalex.org/W2611932403","https://openalex.org/W2612706635","https://openalex.org/W2752782242","https://openalex.org/W2756050327","https://openalex.org/W2795089319","https://openalex.org/W2797184202","https://openalex.org/W2807744618","https://openalex.org/W2809890486","https://openalex.org/W2888934629","https://openalex.org/W2895689136","https://openalex.org/W2916798096","https://openalex.org/W2940457086","https://openalex.org/W2944006115","https://openalex.org/W2949662773","https://openalex.org/W2957744218","https://openalex.org/W2962811204","https://openalex.org/W2962896489","https://openalex.org/W2963076818","https://openalex.org/W2963598138","https://openalex.org/W2963995996","https://openalex.org/W2964014798","https://openalex.org/W2964016027","https://openalex.org/W2964134613","https://openalex.org/W2964221239","https://openalex.org/W2964318832","https://openalex.org/W2968459013","https://openalex.org/W2972662547","https://openalex.org/W2982627166","https://openalex.org/W2996249958","https://openalex.org/W2996835428","https://openalex.org/W3034217102","https://openalex.org/W3034999503","https://openalex.org/W3035050855","https://openalex.org/W3035225512","https://openalex.org/W3035385851","https://openalex.org/W3049455300","https://openalex.org/W3081460284","https://openalex.org/W3106882556","https://openalex.org/W3108496296","https://openalex.org/W3136525061","https://openalex.org/W3169891778","https://openalex.org/W3183842024","https://openalex.org/W3195639294","https://openalex.org/W3205327953","https://openalex.org/W4281249524","https://openalex.org/W4289752563","https://openalex.org/W4313068951","https://openalex.org/W4382457852","https://openalex.org/W4386083126"],"related_works":[],"abstract_inverted_index":{"3D":[0,212],"human":[1],"pose":[2,68,74,214,217],"estimation":[3],"from":[4],"2D":[5,67],"keypoint":[6],"observation":[7],"has":[8],"been":[9],"used":[10],"in":[11,45],"many":[12],"human-centered":[13],"computer":[14],"vision":[15],"applications.":[16],"In":[17],"this":[18,109],"work,":[19],"we":[20,125,151],"tackle":[21],"the":[22,39,99,105,117,131,182],"task":[23],"by":[24,76,190],"formulating":[25],"a":[26,59,70,154],"novel":[27],"grid":[28,35,73,135,145,156,168,184,199],"representation":[29,112],"learning":[30,113,169],"paradigm":[31],"that":[32,181],"relies":[33,163],"on":[34,52,164,193],"convolution":[36,43,136],"(GridConv),":[37],"mimicking":[38],"wisdom":[40],"of":[41,108,119],"regular":[42,71],"operations":[44,137],"image":[46],"space.":[47],"GridConv":[48,120],"is":[49,102],"defined":[50],"based":[51],"Semantic":[53],"Grid":[54],"Transformation":[55],"(SGT)":[56],"which":[57,162],"leverages":[58],"binary":[60],"assignment":[61],"matrix":[62],"to":[63,82,94,121,171],"map":[64],"standard":[65],"skeleton":[66],"onto":[69],"weave-like":[72],"joint":[75,176],"joint.":[77],"We":[78],"provide":[79],"two":[80],"ways":[81],"implement":[83],"SGT:":[84],"handcrafted":[85],"and":[86,98,140,174,195,219],"learnable":[87,100],"SGT.":[88],"Surprisingly,":[89],"both":[90],"designs":[91],"turn":[92],"out":[93],"achieve":[95],"promising":[96],"results":[97],"one":[101],"better,":[103],"demonstrating":[104],"great":[106],"potential":[107],"new":[110],"lifting":[111,146,157,185,200],"formulation.":[114],"To":[115],"improve":[116],"ability":[118,206],"encode":[122,172],"contextual":[123],"cues,":[124],"introduce":[126],"an":[127,165],"attention":[128],"module":[129],"over":[130],"convolutional":[132],"kernel,":[133],"making":[134],"input-dependent,":[138],"spatial-aware":[139],"grid-specific.":[141],"Besides":[142],"our":[143],"spatial":[144,173],"network":[147,158,186],"for":[148,159],"single-frame":[149],"input,":[150,161],"also":[152,202],"present":[153],"spatial-temporal":[155],"video-based":[160],"efficient":[166],"multi-scale":[167],"strategy":[170],"temporal":[175],"variations.":[177],"Extensive":[178],"experiments":[179],"demonstrate":[180],"proposed":[183],"outperforms":[187],"existing":[188],"approaches":[189],"remarkable":[191],"margins":[192],"Human3.6M":[194],"MPI-INF-3DHP":[196],"datasets.":[197],"Our":[198],"networks":[201],"exhibit":[203],"good":[204],"generalization":[205],"across":[207],"three":[208],"other":[209],"keypoint-based":[210],"tasks:":[211],"hand":[213],"estimation,":[215,218],"head":[216],"action":[220],"recognition.":[221]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-03T00:00:00"}