{"id":"https://openalex.org/W4408323594","doi":"https://doi.org/10.1109/tcsvt.2025.3548845","title":"Vision-Semantics-Label: A New Two-Step Paradigm for Action Recognition With Large Language Model","display_name":"Vision-Semantics-Label: A New Two-Step Paradigm for Action Recognition With Large Language Model","publication_year":2025,"publication_date":"2025-03-11","ids":{"openalex":"https://openalex.org/W4408323594","doi":"https://doi.org/10.1109/tcsvt.2025.3548845"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3548845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3548845","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/A5073172997","display_name":"Xiaoyu Chen","orcid":"https://orcid.org/0000-0002-7673-265X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Chen","raw_affiliation_strings":["State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071889746","display_name":"Wanru Xu","orcid":"https://orcid.org/0000-0003-2206-5051"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanru Xu","raw_affiliation_strings":["State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025341442","display_name":"Shichao Kan","orcid":"https://orcid.org/0000-0003-0097-6196"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichao Kan","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linna Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linna Zhang","raw_affiliation_strings":["College of Mechanical Engineering, Guizhou University, Guiyang, Guizhou, China"],"affiliations":[{"raw_affiliation_string":"College of Mechanical Engineering, Guizhou University, Guiyang, Guizhou, China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033896100","display_name":"Yi Jin","orcid":"https://orcid.org/0000-0001-8408-3816"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Jin","raw_affiliation_strings":["State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082462498","display_name":"Yigang Cen","orcid":"https://orcid.org/0000-0001-6255-9422"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yigang Cen","raw_affiliation_strings":["State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010019122","display_name":"Yidong Li","orcid":"https://orcid.org/0000-0003-2965-6196"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Li","raw_affiliation_strings":["State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5073172997"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":5.1136,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94887233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"2","first_page":"1313","last_page":"1327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8130000233650208,"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":0.8130000233650208,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.6972000002861023,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.6851999759674072,"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":0.7687075734138489},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5692863464355469},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5631290674209595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5554903149604797},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42919921875},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3514062762260437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33073121309280396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687075734138489},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5692863464355469},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5631290674209595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554903149604797},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42919921875},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3514062762260437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33073121309280396},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3548845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3548845","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/G3644680343","display_name":null,"funder_award_id":"62463002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G53838021","display_name":null,"funder_award_id":"62473033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8222222245","display_name":null,"funder_award_id":"62202499","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2101105183","https://openalex.org/W2126579184","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2944006115","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964134613","https://openalex.org/W3035254087","https://openalex.org/W3097283600","https://openalex.org/W3126721948","https://openalex.org/W4214612132","https://openalex.org/W4281737392","https://openalex.org/W4296079457","https://openalex.org/W4297697565","https://openalex.org/W4309880619","https://openalex.org/W4312254032","https://openalex.org/W4312270234","https://openalex.org/W4312894178","https://openalex.org/W4313886816","https://openalex.org/W4322731056","https://openalex.org/W4368232702","https://openalex.org/W4382467086","https://openalex.org/W4385245566","https://openalex.org/W4386065554","https://openalex.org/W4386065852","https://openalex.org/W4386076522","https://openalex.org/W4387967959","https://openalex.org/W4389519587","https://openalex.org/W4390872366","https://openalex.org/W4394896960","https://openalex.org/W4396793540","https://openalex.org/W4399310957","https://openalex.org/W4402671548","https://openalex.org/W4402716381","https://openalex.org/W4402727142","https://openalex.org/W4402727584","https://openalex.org/W4402754220","https://openalex.org/W4404915370","https://openalex.org/W4406360558","https://openalex.org/W7108068597"],"related_works":["https://openalex.org/W4231937131","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W1480341462","https://openalex.org/W598950423","https://openalex.org/W4256673449","https://openalex.org/W2084487854","https://openalex.org/W4292559016"],"abstract_inverted_index":{"In":[0,114,150],"recent":[1],"years,":[2],"the":[3,13,52,115,135,141,146,151,176,188,196,212],"rapid":[4],"advancement":[5],"of":[6,15,54,145,215],"multi-modal":[7],"large":[8,98,108,124,147,216],"language":[9,99,109,125,148,217],"models":[10,33,61,110,218],"has":[11],"propelled":[12],"development":[14],"video-based":[16,107],"conversation":[17],"models.":[18,56],"Due":[19],"to":[20,104,132,185,198],"their":[21,77],"exceptional":[22],"video":[23,65],"understanding":[24],"capabilities,":[25],"there":[26],"is":[27],"often":[28],"an":[29],"expectation":[30],"that":[31,187],"these":[32,59,86],"can":[34,169],"handle":[35],"all":[36,164],"video-related":[37],"tasks,":[38],"including":[39],"action":[40,44,74,112,173,182,193,201,220],"recognition.":[41,113,202,221],"However,":[42],"because":[43],"recognition":[45,183],"datasets":[46,184],"typically":[47],"lack":[48],"semantic":[49,181],"information,":[50],"limiting":[51],"performance":[53,214],"dialogue":[55,60],"Additionally,":[57],"as":[58],"are":[62,227],"designed":[63,155],"for":[64,73,111,134],"understanding,":[66],"they":[67],"frequently":[68],"overlook":[69],"critical":[70],"information":[71],"required":[72],"recognition\u2014continuous":[75],"motion\u2014in":[76],"model":[78,126,197],"architecture":[79],"and":[80,163,225],"training":[81,189],"dataset":[82,226],"configurations.":[83],"To":[84],"address":[85],"challenges,":[87],"we":[88,118,154,179],"first":[89,116],"propose":[90],"a":[91,120],"novel":[92],"two-step":[93],"mapping":[94,157],"framework":[95],"based":[96],"on":[97,207],"models,":[100],"termed":[101],"\u201cVision-Semantics-Label\u201d":[102],"mapping,":[103],"better":[105,199],"adapt":[106],"step,":[117,153],"proposed":[119],"visual-skeletal":[121],"collaborative":[122],"learning":[123],"(VS-LLM),":[127],"which":[128,168],"utilizes":[129],"human":[130],"keypoints":[131],"compensate":[133],"missing":[136],"motion":[137],"details":[138],"without":[139],"increasing":[140],"input":[142],"token":[143],"length":[144],"model.":[149],"second":[152],"two":[156],"methods:":[158],"verb":[159],"noun":[160],"match":[161,166],"(VN-Match)":[162],"text":[165],"(ALL-Match),":[167],"effectively":[170],"extract":[171],"relevant":[172],"descriptions":[174],"from":[175],"text.":[177],"Finally,":[178],"construct":[180],"ensure":[186],"data":[190],"inherently":[191],"contains":[192],"details,":[194],"enabling":[195],"achieve":[200],"We":[203],"evaluate":[204],"our":[205],"approach":[206],"five":[208],"benchmark":[209],"datasets,":[210],"demonstrating":[211],"state-of-the-art":[213],"in":[219],"The":[222],"source":[223],"code":[224],"publicly":[228],"available":[229],"at":[230],"https://github.com/xiaoyu92568/VS-LLM.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}