{"id":"https://openalex.org/W4392904192","doi":"https://doi.org/10.1109/icassp48485.2024.10447118","title":"Open-Vocabulary Skeleton Action Recognition with Diffusion Graph Convolutional Network and Pre-Trained Vision-Language Models","display_name":"Open-Vocabulary Skeleton Action Recognition with Diffusion Graph Convolutional Network and Pre-Trained Vision-Language Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904192","doi":"https://doi.org/10.1109/icassp48485.2024.10447118"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447118","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/A5100679851","display_name":"Chao Wei","orcid":"https://orcid.org/0000-0002-2278-7057"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Chao Wei","raw_affiliation_strings":["Institute for Artificial Intelligence at Tsinghua University (THUAI),Beijing National Research Center for Information Science and Technology (BNRist)","Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence at Tsinghua University (THUAI)","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence at Tsinghua University (THUAI),Beijing National Research Center for Information Science and Technology (BNRist)","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence at Tsinghua University (THUAI)","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011846","display_name":"Zhidong Deng","orcid":"https://orcid.org/0000-0001-9970-1023"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Zhidong Deng","raw_affiliation_strings":["Institute for Artificial Intelligence at Tsinghua University (THUAI),Beijing National Research Center for Information Science and Technology (BNRist)","Department of Computer Science and Technology, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence at Tsinghua University (THUAI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence at Tsinghua University (THUAI),Beijing National Research Center for Information Science and Technology (BNRist)","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence at Tsinghua University (THUAI)","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3195","last_page":"3199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9929999709129333,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.98580002784729,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7493162155151367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7087821960449219},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.5894403457641602},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5007741451263428},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.47874540090560913},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.47416773438453674},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4415648281574249},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43325892090797424},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43301844596862793},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4303818345069885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40421000123023987},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3573371171951294},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19079101085662842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493162155151367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7087821960449219},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.5894403457641602},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5007741451263428},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.47874540090560913},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.47416773438453674},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4415648281574249},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43325892090797424},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43301844596862793},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4303818345069885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40421000123023987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3573371171951294},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19079101085662842},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447118","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G4700434351","display_name":null,"funder_award_id":"2019GQG0002","funder_id":"https://openalex.org/F4320322392","funder_display_name":"Tsinghua University"},{"id":"https://openalex.org/G5541826327","display_name":null,"funder_award_id":"62176134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2054041160","https://openalex.org/W2603705233","https://openalex.org/W2619947201","https://openalex.org/W2798991696","https://openalex.org/W2944006115","https://openalex.org/W2963076818","https://openalex.org/W2963283377","https://openalex.org/W2964015378","https://openalex.org/W2964134613","https://openalex.org/W2970791029","https://openalex.org/W2972073579","https://openalex.org/W2978508283","https://openalex.org/W3092923133","https://openalex.org/W3100646853","https://openalex.org/W3105346780","https://openalex.org/W3176445421","https://openalex.org/W3195429019","https://openalex.org/W3209532394","https://openalex.org/W4200477908","https://openalex.org/W4225323055","https://openalex.org/W4297808394","https://openalex.org/W4312372834","https://openalex.org/W4312554543","https://openalex.org/W4312818263","https://openalex.org/W4318348288","https://openalex.org/W6784977419","https://openalex.org/W6791353385","https://openalex.org/W6810334672","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"This":[0],"study":[1],"explores":[2],"unsupervised":[3],"open-vocabulary":[4,97],"skeleton":[5,32,54,86,112,122],"action":[6,123],"recognition,":[7],"aiming":[8],"at":[9],"addressing":[10],"inaccurate":[11],"spatial":[12,59],"matching":[13],"and":[14,42,60,79,109,134,138],"poor":[15],"interpretability":[16],"of":[17,31,68,104],"existing":[18],"GCN":[19],"models.":[20],"We":[21,114],"present":[22],"Skeleton-DGCFA,":[23],"an":[24],"approach":[25],"to":[26,84],"make":[27],"feature":[28],"alignment":[29],"(FA)":[30],"with":[33,47,94,101],"image":[34],"modalities":[35],"based":[36],"on":[37,90,136],"a":[38,116],"large":[39],"pre-trained":[40,106],"vision":[41],"language":[43],"(VL)":[44],"model":[45,108],"along":[46],"our":[48,110],"new":[49,117],"diffusion":[50,67],"graph":[51,70],"convolutional":[52,62],"(DGC)":[53],"encoder.":[55,113],"The":[56,96],"DGC":[57,111],"comprises":[58],"temporal":[61],"modules,":[63],"allowing":[64],"for":[65],"the":[66,85,102,105,120,128],"different":[69],"semantic":[71],"features.":[72],"Skeleton-DGCFA":[73],"harnesses":[74],"recent":[75],"large-scale":[76],"VL":[77,107],"models":[78],"extends":[80],"their":[81],"zero-shot":[82,98,121,130],"capabilities":[83,99],"modality":[87],"by":[88,132],"capitalizing":[89],"its":[91],"natural":[92],"pairing":[93],"images.":[95],"improve":[100],"strength":[103],"establish":[115],"state-of-the-art":[118],"in":[119],"recognition":[124],"tasks,":[125],"significantly":[126],"surpassing":[127],"vanilla":[129],"method":[131],"27.0%":[133],"19.7%":[135],"NTU-60":[137],"NTU-120,":[139],"respectively.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}