{"id":"https://openalex.org/W4403791723","doi":"https://doi.org/10.1145/3664647.3681015","title":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","display_name":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791723","doi":"https://doi.org/10.1145/3664647.3681015"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101763630","display_name":"Jinfu Liu","orcid":"https://orcid.org/0009-0001-0994-9146"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfu Liu","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-0994-9146","affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418568","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3957-7061"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0003-3957-7061","affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705472","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0002-6332-8316"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyuan Liu","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6332-8316","affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4909","last_page":"4918"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9952999949455261,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7714415192604065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891608238220215},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.6321382522583008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5345895290374756},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4923664331436157},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.43631571531295776}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7714415192604065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891608238220215},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.6321382522583008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5345895290374756},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4923664331436157},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43631571531295776},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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:10.1145/3664647.3681015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1893516992","https://openalex.org/W2054041160","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2296311849","https://openalex.org/W2593146028","https://openalex.org/W2604321021","https://openalex.org/W2606294640","https://openalex.org/W2739179646","https://openalex.org/W2792140610","https://openalex.org/W2793547936","https://openalex.org/W2795354662","https://openalex.org/W2868755588","https://openalex.org/W2944006115","https://openalex.org/W2962722475","https://openalex.org/W2962850006","https://openalex.org/W2963076818","https://openalex.org/W2964347220","https://openalex.org/W3035050855","https://openalex.org/W3035570025","https://openalex.org/W3093411241","https://openalex.org/W3096803658","https://openalex.org/W3106327734","https://openalex.org/W3109392981","https://openalex.org/W3123784868","https://openalex.org/W3141495342","https://openalex.org/W3172117784","https://openalex.org/W3174836262","https://openalex.org/W3195949276","https://openalex.org/W3203634062","https://openalex.org/W3207613026","https://openalex.org/W4282943820","https://openalex.org/W4283775680","https://openalex.org/W4304092056","https://openalex.org/W4312245820","https://openalex.org/W4319299930","https://openalex.org/W4367663575","https://openalex.org/W4382449787","https://openalex.org/W4386065362","https://openalex.org/W4386065691","https://openalex.org/W4386075985","https://openalex.org/W4386076069","https://openalex.org/W4387968033","https://openalex.org/W4389169911","https://openalex.org/W4389665476","https://openalex.org/W4390871756","https://openalex.org/W4390871806","https://openalex.org/W4390871852","https://openalex.org/W4390874024","https://openalex.org/W4390874324","https://openalex.org/W4401413845","https://openalex.org/W4401990989","https://openalex.org/W4401991041","https://openalex.org/W4401991047"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2953562271","https://openalex.org/W2334655667","https://openalex.org/W2374013449","https://openalex.org/W1576128429","https://openalex.org/W4399611050","https://openalex.org/W2269464716","https://openalex.org/W2999049608","https://openalex.org/W3170431411"],"abstract_inverted_index":{"Skeleton-based":[0],"action":[1,80,210,231],"recognition":[2,211],"has":[3],"garnered":[4],"significant":[5],"attention":[6],"due":[7],"to":[8,147,184],"the":[9,17,54,68,88,110,133,153,166,170,175,200,207,221],"utilization":[10],"of":[11,19,106,156,202,224],"concise":[12,97],"and":[13,35,45,51,91,122,144,169,178,195,217,229],"resilient":[14],"skeletons.":[15],"Nevertheless,":[16],"absence":[18],"detailed":[20],"body":[21],"information":[22,143],"in":[23,84,99,180,227],"skeletons":[24,98],"restricts":[25],"performance,":[26],"while":[27],"other":[28],"multimodal":[29,40,56,69,157],"methods":[30],"require":[31],"substantial":[32],"inference":[33,46],"resources":[34],"are":[36],"inefficient":[37],"when":[38],"using":[39],"data":[41],"during":[42,87],"both":[43],"training":[44,89],"stages.":[47],"To":[48],"address":[49],"this":[50],"fully":[52],"harness":[53],"complementary":[55],"features,":[57],"we":[58],"propose":[59],"a":[60,181],"novel":[61],"multi-modality":[62,85],"co-learning":[63,86],"(MMCL)":[64],"framework":[65,103],"by":[66,94],"leveraging":[67],"large":[70],"language":[71],"models":[72],"(LLMs)":[73],"as":[74],"auxiliary":[75],"networks":[76],"for":[77],"efficient":[78],"skeleton-based":[79,209],"recognition,":[81],"which":[82,205],"engages":[83],"stage":[90],"keeps":[92],"efficiency":[93],"employing":[95],"only":[96],"inference.":[100],"Our":[101,233],"MMCL":[102,226],"primarily":[104],"consists":[105],"two":[107],"modules.":[108],"First,":[109],"Feature":[111,134],"Alignment":[112],"Module":[113,136],"(FAM)":[114],"extracts":[115],"rich":[116],"RGB":[117,139],"features":[118,128,150,162],"from":[119],"video":[120],"frames":[121],"aligns":[123],"them":[124],"with":[125,141],"global":[126],"skeleton":[127],"via":[129],"contrastive":[130],"learning.":[131],"Second,":[132],"Refinement":[135],"(FRM)":[137],"uses":[138],"images":[140],"temporal":[142],"text":[145,161],"instruction":[146],"generate":[148],"instructive":[149,160],"based":[151],"on":[152,189,215],"powerful":[154],"generalization":[155,179,223],"LLMs.":[158],"These":[159],"will":[163,173],"further":[164],"refine":[165],"classification":[167],"scores":[168,172],"refined":[171],"enhance":[174],"model's":[176],"robustness":[177],"manner":[182],"similar":[183],"soft":[185],"labels.":[186],"Extensive":[187],"experiments":[188,214],"NTU":[190,192],"RGB+D,":[191],"RGB+D":[193],"120":[194],"Northwestern-UCLA":[196],"benchmarks":[197],"consistently":[198],"verify":[199],"effectiveness":[201],"our":[203,225],"MMCL,":[204],"outperforms":[206],"existing":[208],"methods.":[212],"Meanwhile,":[213],"UTD-MHAD":[216],"SYSU-Action":[218],"datasets":[219],"demonstrate":[220],"commendable":[222],"zero-shot":[228],"domain-adaptive":[230],"recognition.":[232],"code":[234],"is":[235],"publicly":[236],"available":[237],"at:":[238],"https://github.com/liujf69/MMCL-Action.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}