{"id":"https://openalex.org/W4402979997","doi":"https://doi.org/10.1109/icme57554.2024.10688034","title":"Enhancing Human Action Recognition with Fine-grained Body Movement Attention","display_name":"Enhancing Human Action Recognition with Fine-grained Body Movement Attention","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979997","doi":"https://doi.org/10.1109/icme57554.2024.10688034"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688034","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5034937978","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-4029-6585"},"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 Center for Data Hub and Security,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Center for Data Hub and Security,Zhejiang,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102658609","display_name":"Junxiao Xue","orcid":null},"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":"Junxiao Xue","raw_affiliation_strings":["Zhejiang Lab,Research Center of Space Based Computing System,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Center of Space Based Computing System,Zhejiang,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Lin","orcid":null},"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":"Feng Lin","raw_affiliation_strings":["Zhejiang Lab,Research Centre for Frontier Fundamental Studies,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Centre for Frontier Fundamental Studies,Zhejiang,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101461905","display_name":"Qing Zhang","orcid":"https://orcid.org/0000-0002-6996-353X"},"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":"Qing Zhang","raw_affiliation_strings":["Zhejiang Lab,Research Centre for Frontier Fundamental Studies,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Centre for Frontier Fundamental Studies,Zhejiang,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361432","display_name":"\u0410. \u0412. \u0421\u043c\u0438\u0440\u043d\u043e\u0432","orcid":"https://orcid.org/0000-0001-5361-8232"},"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":"Pavel Smirnov","raw_affiliation_strings":["Zhejiang Lab,Research Center for Astronomical Computing,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Center for Astronomical Computing,Zhejiang,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597357","display_name":"Xiao Ma","orcid":"https://orcid.org/0000-0002-0261-0369"},"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":"Xiao Ma","raw_affiliation_strings":["Zhejiang Lab,Research Centre for Frontier Fundamental Studies,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Centre for Frontier Fundamental Studies,Zhejiang,China","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 Center for Data Hub and Security,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Research Center for Data Hub and Security,Zhejiang,China","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9704999923706055,"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":0.9704999923706055,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9143999814987183,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6829777956008911},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6783146858215332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6374086141586304},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5896346569061279},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46177375316619873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2882242798805237}],"concepts":[{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6829777956008911},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6783146858215332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6374086141586304},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5896346569061279},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46177375316619873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2882242798805237},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","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/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},{"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/icme57554.2024.10688034","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"In":[0],"the":[1,50,67,79],"field":[2],"of":[3],"vision-language":[4],"models":[5,18],"(VLMs),":[6],"human":[7],"action":[8],"recognition":[9],"models,":[10,107],"while":[11,110],"effective,":[12],"always":[13],"rely":[14],"on":[15,44],"large":[16],"pre-trained":[17,64],"or":[19],"high-resolution":[20],"inputs,":[21],"leading":[22],"to":[23,38,52],"computational":[24,112],"challenges.":[25],"To":[26],"address":[27],"this,":[28],"we":[29,48],"propose":[30],"a":[31,99],"novel":[32],"VLM":[33],"approach":[34],"with":[35,93],"fine-grained":[36,56,68],"attention":[37],"body":[39,57],"movements.":[40],"Unlike":[41],"methods":[42],"relying":[43],"coarse":[45],"video-text":[46],"matching,":[47],"guide":[49],"model":[51,85],"infer":[53],"actions":[54],"from":[55,73],"part":[58],"movements":[59],"using":[60],"two":[61],"techniques:":[62],"fine-tuning":[63],"encoders":[65],"at":[66,78],"level":[69],"and":[70,75,90,98],"matching":[71],"labels":[72],"language":[74],"vision":[76],"perspectives":[77],"coarse-grained":[80],"level.":[81],"Experiments":[82],"show":[83],"our":[84],"excels":[86],"in":[87],"fully-supervised,":[88],"few-shot,":[89],"zero-shot":[91],"scenarios":[92],"just":[94],"8":[95],"random":[96],"frames":[97],"ViT-B/32":[100],"backbone.":[101],"It":[102],"outperforms":[103],"most":[104],"ViT-L/14":[105],"based":[106],"demonstrating":[108],"effectiveness":[109],"saving":[111],"resources.":[113],"The":[114],"largest":[115],"Top-1":[116],"accuracy":[117],"improvement":[118],"over":[119],"second-best":[120],"approaches":[121],"is":[122],"6.8%.":[123]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}