{"id":"https://openalex.org/W4404035381","doi":"https://doi.org/10.1109/tcsvt.2024.3491176","title":"Enhancing Skeleton-Based Action Recognition With Language Descriptions From Pre-Trained Large Multimodal Models","display_name":"Enhancing Skeleton-Based Action Recognition With Language Descriptions From Pre-Trained Large Multimodal Models","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404035381","doi":"https://doi.org/10.1109/tcsvt.2024.3491176"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3491176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3491176","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/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":true,"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/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":false,"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/A5101718919","display_name":"Xu Gao","orcid":"https://orcid.org/0000-0003-4424-5651"},"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":"Xu Gao","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/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/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 Orthopedics Hospital of Chengdu, Chengdu, China","No.1 Orthopedics Hospital of Chengdu, China"],"affiliations":[{"raw_affiliation_string":"No.1 Orthopedics Hospital of Chengdu, Chengdu, China","institution_ids":[]},{"raw_affiliation_string":"No.1 Orthopedics Hospital of 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":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052482693"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.4499,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90606878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"35","issue":"3","first_page":"2118","last_page":"2132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9970999956130981,"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":0.9970999956130981,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9728000164031982,"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":0.7155014276504517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5716991424560547},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.5674937963485718},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.547271728515625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.530163586139679},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4081788659095764},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.360222190618515},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33865657448768616},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.1104113757610321},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10590454936027527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155014276504517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716991424560547},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.5674937963485718},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.547271728515625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.530163586139679},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4081788659095764},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.360222190618515},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33865657448768616},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.1104113757610321},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10590454936027527}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3491176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3491176","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1356151750","display_name":null,"funder_award_id":"2021YFS0016","funder_id":"https://openalex.org/F4320336596","funder_display_name":"Key Research and Development Program of Sichuan Province"},{"id":"https://openalex.org/G2563345526","display_name":null,"funder_award_id":"62473079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G275970464","display_name":null,"funder_award_id":"61971106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4819900270","display_name":null,"funder_award_id":"No.2021YFS0016","funder_id":"https://openalex.org/F4320336596","funder_display_name":"Key Research and Development Program of Sichuan Province"},{"id":"https://openalex.org/G6263283406","display_name":null,"funder_award_id":"2021-YF05-02388-SN","funder_id":"https://openalex.org/F4320309892","funder_display_name":"Citrus Research and Development Foundation"},{"id":"https://openalex.org/G6552395178","display_name":null,"funder_award_id":"No. 61971106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309892","display_name":"Citrus Research and Development Foundation","ror":"https://ror.org/02y3ad647"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336596","display_name":"Key Research and Development Program of Sichuan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1744759976","https://openalex.org/W1950788856","https://openalex.org/W2593146028","https://openalex.org/W2606294640","https://openalex.org/W2716916105","https://openalex.org/W2725422033","https://openalex.org/W2736334449","https://openalex.org/W2765433083","https://openalex.org/W2772805989","https://openalex.org/W2792140610","https://openalex.org/W2793547936","https://openalex.org/W2799211965","https://openalex.org/W2922355425","https://openalex.org/W2940457086","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2962815362","https://openalex.org/W2963076818","https://openalex.org/W2963369114","https://openalex.org/W2963465695","https://openalex.org/W2963901033","https://openalex.org/W2964134613","https://openalex.org/W2964138343","https://openalex.org/W2972327058","https://openalex.org/W2981356320","https://openalex.org/W3002271958","https://openalex.org/W3034999503","https://openalex.org/W3035050855","https://openalex.org/W3035225512","https://openalex.org/W3035637814","https://openalex.org/W3092754310","https://openalex.org/W3093411241","https://openalex.org/W3097033071","https://openalex.org/W3100950981","https://openalex.org/W3108496296","https://openalex.org/W3109392981","https://openalex.org/W3115431207","https://openalex.org/W3125955391","https://openalex.org/W3159212182","https://openalex.org/W3159393405","https://openalex.org/W3165978997","https://openalex.org/W3174562241","https://openalex.org/W3174836262","https://openalex.org/W3175624454","https://openalex.org/W3185273257","https://openalex.org/W3203634062","https://openalex.org/W3213518743","https://openalex.org/W4205947138","https://openalex.org/W4282943820","https://openalex.org/W4292970178","https://openalex.org/W4294663760","https://openalex.org/W4312245820","https://openalex.org/W4312563428","https://openalex.org/W4312638762","https://openalex.org/W4312661503","https://openalex.org/W4312757522","https://openalex.org/W4312956471","https://openalex.org/W4313136445","https://openalex.org/W4320015918","https://openalex.org/W4385245566","https://openalex.org/W4386065362","https://openalex.org/W4386065571","https://openalex.org/W4386066126","https://openalex.org/W4387643384","https://openalex.org/W4390327397","https://openalex.org/W4390871852","https://openalex.org/W4390873343","https://openalex.org/W4390873402","https://openalex.org/W4391248734","https://openalex.org/W4391306099","https://openalex.org/W4391516381","https://openalex.org/W4401023909","https://openalex.org/W4402727764","https://openalex.org/W4402775313","https://openalex.org/W4403791723","https://openalex.org/W6682864246","https://openalex.org/W6754693662","https://openalex.org/W6770370219","https://openalex.org/W6791353385","https://openalex.org/W6799178971","https://openalex.org/W6804416512","https://openalex.org/W6811013733","https://openalex.org/W6849177959","https://openalex.org/W6850204008","https://openalex.org/W6850787431","https://openalex.org/W6851592950"],"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/W4399611050","https://openalex.org/W3170431411"],"abstract_inverted_index":{"Skeleton":[0],"data":[1,53,126],"has":[2],"become":[3],"popular":[4],"in":[5,13,33,124],"human":[6,15],"action":[7,65,169,180],"recognition":[8,66,170,181],"because":[9],"of":[10,22,71,90,158,166],"its":[11],"efficacy":[12],"capturing":[14],"motion":[16],"patterns":[17],"while":[18,67],"mitigating":[19],"the":[20,69,86,102,120,156,164],"influence":[21],"environmental":[23,29,61,131],"noise.":[24],"However,":[25],"overlooking":[26],"critical":[27],"action-related":[28,97],"descriptors":[30],"presents":[31],"challenges":[32],"distinguishing":[34],"actions":[35],"characterized":[36],"by":[37],"similar":[38],"body":[39],"movements.":[40],"To":[41],"address":[42],"this":[43],"limitation,":[44],"we":[45,109,134],"propose":[46,135],"a":[47,77,111],"novel":[48],"framework":[49],"that":[50,84,118],"integrates":[51],"skeleton":[52,125,149],"with":[54],"language":[55,98,151],"descriptions":[56,100],"to":[57,94,104,127,142],"easily":[58],"capture":[59],"essential":[60],"information":[62],"for":[63],"fine-grained":[64],"maintaining":[68],"robustness":[70],"skeleton-based":[72,168,179],"methods.":[73],"We":[74],"first":[75],"develop":[76],"Language":[78],"Environment":[79,113],"Description":[80],"Generation":[81],"(LEDG)":[82],"module":[83,117,141],"utilizes":[85],"open-world":[87],"understanding":[88],"ability":[89],"Large":[91],"Multimodal":[92],"Models":[93],"generate":[95],"instance-level":[96],"environment":[99],"without":[101],"need":[103],"train":[105],"additional":[106],"modules.":[107],"Then,":[108],"introduce":[110],"Skeleton-supported":[112],"Feature":[114,138],"Extraction":[115],"(SEFE)":[116],"leverages":[119],"temporal":[121],"dependency":[122],"inherent":[123],"extract":[128],"key":[129],"semantic":[130],"features.":[132],"Additionally,":[133],"an":[136],"Entropy-based":[137],"Fusion":[139],"(EFF)":[140],"dynamically":[143],"amalgamate":[144],"complementary":[145],"features":[146],"from":[147],"both":[148],"and":[150,172],"domains.":[152],"Experimental":[153],"results":[154],"demonstrate":[155],"superiority":[157],"our":[159],"framework,":[160],"which":[161],"can":[162],"improve":[163],"accuracy":[165],"existing":[167],"methods":[171],"achieve":[173],"state-of-the-art":[174],"performance":[175],"on":[176],"four":[177],"well-established":[178],"benchmarks.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}