{"id":"https://openalex.org/W4392903964","doi":"https://doi.org/10.1109/icassp48485.2024.10445852","title":"Video-Language Graph Convolutional Network for Human Action Recognition","display_name":"Video-Language Graph Convolutional Network for Human Action Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903964","doi":"https://doi.org/10.1109/icassp48485.2024.10445852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100422063","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-6001-3167"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026380797","display_name":"Xiaoran Yan","orcid":"https://orcid.org/0000-0003-3481-1832"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoran Yan","raw_affiliation_strings":["Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Institute of Artificial Intelligence,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":2.1035,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90316211,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7995","last_page":"7999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.9975000023841858,"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":0.989799976348877,"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":0.8857787251472473},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.7445592880249023},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6527268886566162},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6111170053482056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6046437621116638},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5201050043106079},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5199136137962341},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4741251468658447},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45560234785079956},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.45089980959892273},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44046902656555176},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4197111427783966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36677801609039307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3424171209335327},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11014807224273682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8857787251472473},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.7445592880249023},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6527268886566162},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6111170053482056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6046437621116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5201050043106079},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5199136137962341},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4741251468658447},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45560234785079956},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.45089980959892273},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44046902656555176},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4197111427783966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36677801609039307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3424171209335327},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11014807224273682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":20,"referenced_works":["https://openalex.org/W2798405286","https://openalex.org/W2963315828","https://openalex.org/W3035047011","https://openalex.org/W3088102655","https://openalex.org/W3133092047","https://openalex.org/W3200114289","https://openalex.org/W4293363567","https://openalex.org/W4304142382","https://openalex.org/W4306317368","https://openalex.org/W4312480274","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312658081","https://openalex.org/W4386065554","https://openalex.org/W6677712025","https://openalex.org/W6726873649","https://openalex.org/W6789526315","https://openalex.org/W6791353385","https://openalex.org/W6801567822","https://openalex.org/W6847518568"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2142145894","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W4292070284","https://openalex.org/W4386298164","https://openalex.org/W4312933959","https://openalex.org/W4229080059","https://openalex.org/W4286257253","https://openalex.org/W2916853871"],"abstract_inverted_index":{"Transferring":[0],"visual":[1],"language":[2],"models":[3],"(VLMs)":[4],"from":[5],"the":[6,10,35,83,95,117,121],"image":[7],"domain":[8,12],"to":[9,53],"video":[11,131],"has":[13],"recently":[14],"yielded":[15],"great":[16],"success":[17],"on":[18,82],"human":[19,55,130],"action":[20,29,87,132],"recognition":[21,25,36],"tasks.":[22],"However,":[23],"standard":[24],"paradigms":[26],"overlook":[27],"fine-grained":[28,51,127],"parsing":[30,88],"knowledge":[31,52,73,128],"that":[32,46,68,92],"could":[33],"enhance":[34],"accuracy.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,63,75,85,99],"novel":[44],"method":[45,60,81,104],"leverages":[47],"both":[48],"coarse-grained":[49],"and":[50,70,90,112,123],"recognize":[54],"actions":[56],"in":[57,74],"videos.":[58],"Our":[59],"consists":[61],"of":[62,125],"video-language":[64],"graph":[65],"convolutional":[66],"network":[67],"integrates":[69],"fuses":[71],"multi-modal":[72],"progressive":[76],"manner.":[77],"We":[78],"evaluate":[79],"our":[80,103],"Kinetics-TPS,":[84],"large-scale":[86],"dataset,":[89],"demonstrate":[91],"it":[93],"outperforms":[94],"state-of-the-art":[96],"methods":[97],"by":[98],"significant":[100],"margin.":[101],"Moreover,":[102],"achieves":[105],"better":[106],"results":[107],"with":[108],"less":[109],"training":[110],"data":[111],"competitive":[113],"computational":[114],"cost":[115],"than":[116],"existing":[118],"methods,":[119],"showing":[120],"effectiveness":[122],"efficiency":[124],"using":[126],"for":[129],"recognition.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}