{"id":"https://openalex.org/W4405717818","doi":"https://doi.org/10.1109/tmm.2024.3521718","title":"Vision-Language Meets the Skeleton: Progressively Distillation With Cross-Modal Knowledge for 3D Action Representation Learning","display_name":"Vision-Language Meets the Skeleton: Progressively Distillation With Cross-Modal Knowledge for 3D Action Representation Learning","publication_year":2024,"publication_date":"2024-12-23","ids":{"openalex":"https://openalex.org/W4405717818","doi":"https://doi.org/10.1109/tmm.2024.3521718"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521718","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5100602455","display_name":"Yang Chen","orcid":"https://orcid.org/0009-0008-5752-1639"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Chen","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052482693","display_name":"Tian He","orcid":"https://orcid.org/0009-0007-1404-7183"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian He","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057544175","display_name":"Junfeng Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Fu","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074029893","display_name":"Ling Wang","orcid":"https://orcid.org/0000-0001-7007-4740"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Wang","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038505509","display_name":"Jingcai Guo","orcid":"https://orcid.org/0000-0002-0449-4525"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingcai Guo","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033804349","display_name":"Ting Hu","orcid":"https://orcid.org/0000-0002-4642-3848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Hu","raw_affiliation_strings":["No.1 Orthopedic Hospital of Chengdu, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"No.1 Orthopedic Hospital of Chengdu, Chengdu, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042965582","display_name":"Hong Cheng","orcid":"https://orcid.org/0000-0001-5532-9530"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Cheng","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100602455"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.49,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67138724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"27","issue":null,"first_page":"2293","last_page":"2303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973000288009644,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973000288009644,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9943000078201294,"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":0.968500018119812,"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/computer-science","display_name":"Computer science","score":0.8049419522285461},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.7089197635650635},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5815279483795166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5635269284248352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5630797743797302},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5078790783882141},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4495762288570404},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.442116379737854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3832589089870453},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3525247573852539},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.335164874792099},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10309085249900818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8049419522285461},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.7089197635650635},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5815279483795166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5635269284248352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630797743797302},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5078790783882141},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4495762288570404},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.442116379737854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3832589089870453},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3525247573852539},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.335164874792099},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10309085249900818},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521718","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6076922228","display_name":null,"funder_award_id":"62102327","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F3642548314","display_name":"NVIDIA AI Technology Center, University of Florida","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2056898157","https://openalex.org/W2510185399","https://openalex.org/W2526041356","https://openalex.org/W2593146028","https://openalex.org/W2601271987","https://openalex.org/W2603861860","https://openalex.org/W2787919227","https://openalex.org/W2944006115","https://openalex.org/W2963076818","https://openalex.org/W2964134613","https://openalex.org/W3034342078","https://openalex.org/W3034548564","https://openalex.org/W3035050855","https://openalex.org/W3092424783","https://openalex.org/W3106776857","https://openalex.org/W3121661476","https://openalex.org/W3169413442","https://openalex.org/W3185273257","https://openalex.org/W3190580390","https://openalex.org/W3203227473","https://openalex.org/W3203514840","https://openalex.org/W3203634062","https://openalex.org/W3204610735","https://openalex.org/W3205106480","https://openalex.org/W3216909972","https://openalex.org/W4200634815","https://openalex.org/W4285157464","https://openalex.org/W4312387119","https://openalex.org/W4312626422","https://openalex.org/W4312757522","https://openalex.org/W4312841534","https://openalex.org/W4313145975","https://openalex.org/W4313185874","https://openalex.org/W4323338522","https://openalex.org/W4382240124","https://openalex.org/W4382459184","https://openalex.org/W4385488815","https://openalex.org/W4386065445","https://openalex.org/W4386065852","https://openalex.org/W4386075765","https://openalex.org/W4386075908","https://openalex.org/W4386076095","https://openalex.org/W4386108371","https://openalex.org/W4386160289","https://openalex.org/W4386160488","https://openalex.org/W4386215080","https://openalex.org/W4387968040","https://openalex.org/W4387968449","https://openalex.org/W4389459415","https://openalex.org/W4390190427","https://openalex.org/W4390871852","https://openalex.org/W4390872019","https://openalex.org/W4390873402","https://openalex.org/W4392678259","https://openalex.org/W4393158799","https://openalex.org/W4399039553","https://openalex.org/W4404612908","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6801567822","https://openalex.org/W6844194202","https://openalex.org/W6851592950","https://openalex.org/W6856449488"],"related_works":["https://openalex.org/W2953562271","https://openalex.org/W2334655667","https://openalex.org/W2464530384","https://openalex.org/W2105938841","https://openalex.org/W4253358700","https://openalex.org/W3139863978","https://openalex.org/W2014897006","https://openalex.org/W1756135943","https://openalex.org/W4247976907","https://openalex.org/W3026162553"],"abstract_inverted_index":{"Skeleton-based":[0],"action":[1,38,93,109,131,182,204],"representation":[2,94,148],"learning":[3,26,82,149,178],"aims":[4],"to":[5,88,151,176],"interpret":[6],"and":[7,27,140,154,163,171,206,221,232],"understand":[8],"human":[9,91],"behaviors":[10],"by":[11,117],"encoding":[12],"the":[13,31,42,50,56,85,96,107,125,129,137,146,156,177,185,190,197,201,229],"skeleton":[14,45,57,92,130,198],"sequences,":[15],"which":[16,123],"can":[17],"be":[18],"categorized":[19],"into":[20],"two":[21],"primary":[22],"training":[23,68],"paradigms:":[24],"supervised":[25],"self-supervised":[28],"learning.":[29],"However,":[30],"former":[32],"one-hot":[33],"classification":[34],"requires":[35,195],"labor-intensive":[36],"predefined":[37],"categories":[39],"annotations,":[40],"while":[41],"latter":[43],"involves":[44],"transformations":[46],"(e.g.,":[47],"cropping)":[48],"in":[49,145],"pretext":[51],"tasks":[52],"that":[53,83,128,225],"may":[54],"impair":[55],"structure.":[58],"To":[59],"address":[60],"these":[61],"challenges,":[62],"we":[63,105,135],"introduce":[64],"a":[65],"novel":[66],"skeleton-based":[67,181],"framework":[69],"(C<inline-formula":[70],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[71,77,80,98,100],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[72],"notation=\"LaTeX\">$^{2}$</tex-math></inline-formula>VL)":[73],"based":[74],"on":[75,214],"<italic":[76,79,97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</i>ross-modal":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</i>ontrastive":[81],"uses":[84],"progressive":[86],"distillation":[87,173],"learn":[89],"task-agnostic":[90],"from":[95,184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">V</i>ision-<italic":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">L</i>anguage":[101],"knowledge":[102,114,161],"prompts.":[103,211],"Specifically,":[104],"establish":[106],"vision-language":[108,113,160,210],"concept":[110],"space":[111,132],"through":[112],"prompts":[115,162],"generated":[116],"pre-trained":[118],"large":[119],"multimodal":[120],"models":[121],"(LMMs),":[122],"enrich":[124],"fine-grained":[126],"details":[127],"lacks.":[133],"Moreover,":[134],"propose":[136],"intra-modal":[138],"self-similarity":[139],"inter-modal":[141],"cross-consistency":[142],"softened":[143],"targets":[144],"cross-modal":[147],"process":[150],"progressively":[152],"control":[153],"guide":[155],"degree":[157],"of":[158,179],"pulling":[159],"corresponding":[164],"skeletons":[165],"closer.":[166],"These":[167],"soft":[168],"instance":[169],"discrimination":[170],"self-knowledge":[172],"strategies":[174],"contribute":[175],"better":[180],"representations":[183],"noisy":[186],"skeleton-vision-language":[187],"pairs.":[188],"During":[189],"inference":[191],"phase,":[192],"our":[193,226],"method":[194,227],"only":[196],"data":[199],"as":[200],"input":[202],"for":[203,209],"recognition":[205],"no":[207],"longer":[208],"Extensive":[212],"experiments":[213],"NTU":[215,218],"RGB+D":[216,219],"60,":[217],"120,":[220],"PKU-MMD":[222],"datasets":[223],"demonstrate":[224],"outperforms":[228],"previous":[230],"methods":[231],"achieves":[233],"state-of-the-art":[234],"results.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}