{"id":"https://openalex.org/W4404059287","doi":"https://doi.org/10.1145/3700878","title":"Joint Mixing Data Augmentation for Skeleton-Based Action Recognition","display_name":"Joint Mixing Data Augmentation for Skeleton-Based Action Recognition","publication_year":2024,"publication_date":"2024-11-05","ids":{"openalex":"https://openalex.org/W4404059287","doi":"https://doi.org/10.1145/3700878"},"language":"en","primary_location":{"id":"doi:10.1145/3700878","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3700878","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3700878","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3700878","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079207253","display_name":"Linhua Xiang","orcid":"https://orcid.org/0000-0002-6738-223X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhua Xiang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China and National Engineering Research Centre of Speech and Language Information Processing, Hefei, China","University of Science and Technology of China, China and National Engineering Research Center of Speech and Language Information Processing, China"],"raw_orcid":"https://orcid.org/0000-0002-6738-223X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China and National Engineering Research Centre of Speech and Language Information Processing, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]},{"raw_affiliation_string":"University of Science and Technology of China, China and National Engineering Research Center of Speech and Language Information Processing, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103123751","display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China and National Engineering Research Centre of Speech and Language Information Processing, Hefei, China","University of Science and Technology of China, China, Institute of Intelligent Machines, Chinese Academy of Sciences, China, and National Engineering Research Center of Speech and Language Information Processing, China"],"raw_orcid":"https://orcid.org/0000-0003-1859-900X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China and National Engineering Research Centre of Speech and Language Information Processing, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]},{"raw_affiliation_string":"University of Science and Technology of China, China, Institute of Intelligent Machines, Chinese Academy of Sciences, China, and National Engineering Research Center of Speech and Language Information Processing, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210099079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3159,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8071284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"21","issue":"4","first_page":"1","last_page":"24"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962000250816345,"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":0.8367328643798828},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7144181728363037},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.5480322241783142},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4905954897403717},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.47950392961502075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43781810998916626},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.41731345653533936},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3676072061061859},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32291579246520996},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.162798672914505},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09365138411521912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367328643798828},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7144181728363037},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5480322241783142},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4905954897403717},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.47950392961502075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43781810998916626},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.41731345653533936},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3676072061061859},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32291579246520996},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.162798672914505},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09365138411521912},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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:10.1145/3700878","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3700878","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3700878","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3700878","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3700878","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3700878","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404059287.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1936750108","https://openalex.org/W2085731903","https://openalex.org/W2099805216","https://openalex.org/W2116341502","https://openalex.org/W2187089797","https://openalex.org/W2312958246","https://openalex.org/W2554408731","https://openalex.org/W2603861860","https://openalex.org/W2606294640","https://openalex.org/W2736334449","https://openalex.org/W2739074143","https://openalex.org/W2788334925","https://openalex.org/W2890579538","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2950568498","https://openalex.org/W2962722475","https://openalex.org/W2963076818","https://openalex.org/W2964134613","https://openalex.org/W2975231468","https://openalex.org/W2992308087","https://openalex.org/W2993496908","https://openalex.org/W2994721977","https://openalex.org/W2999237480","https://openalex.org/W3034999503","https://openalex.org/W3035050855","https://openalex.org/W3096803658","https://openalex.org/W3113067059","https://openalex.org/W3203634062","https://openalex.org/W3204447181","https://openalex.org/W3205898195","https://openalex.org/W4200633254","https://openalex.org/W4236965008","https://openalex.org/W4283396563","https://openalex.org/W4308497268","https://openalex.org/W4312761717","https://openalex.org/W4312805142","https://openalex.org/W4320015918","https://openalex.org/W4386065362","https://openalex.org/W4386065571","https://openalex.org/W4387968033","https://openalex.org/W4390873402","https://openalex.org/W4390874423","https://openalex.org/W4391216149","https://openalex.org/W4391454521","https://openalex.org/W4393154025","https://openalex.org/W4394897015"],"related_works":["https://openalex.org/W2953562271","https://openalex.org/W2334655667","https://openalex.org/W2464530384","https://openalex.org/W2105938841","https://openalex.org/W4253358700","https://openalex.org/W3139863978","https://openalex.org/W1576128429","https://openalex.org/W4399611050","https://openalex.org/W2269464716","https://openalex.org/W3170431411"],"abstract_inverted_index":{"Skeleton-based":[0],"action":[1,26,102,263,315],"recognition":[2,103,264,316],"is":[3,66,256,282],"beneficial":[4],"for":[5,246],"understanding":[6],"human":[7],"behavior":[8],"in":[9,17,25,52,72,161],"videos,":[10],"and":[11,57,97,175,224,258,280,296,305],"thus":[12],"has":[13],"received":[14],"much":[15],"attention":[16],"recent":[18],"years":[19],"as":[20],"an":[21],"important":[22],"research":[23,29],"area":[24],"recognition.":[27],"Current":[28],"focuses":[30],"on":[31,170,292,311],"designing":[32],"more":[33],"advanced":[34],"algorithms":[35],"to":[36,46,68,70,143,183,219,261,301],"better":[37],"extract":[38],"spatio-temporal":[39],"information":[40,123,134],"from":[41],"skeleton":[42,55,121,162,173,205],"data.":[43,206],"However,":[44],"due":[45],"the":[47,53,58,95,118,131,140,145,158,171,185,193,267,270,277,303,308],"small":[48],"amount":[49],"of":[50,60,99,107,249,272,307],"data":[51,62,83,148,188,202,212,243],"existing":[54],"dataset":[56],"lack":[59],"effective":[61],"augmentation":[63,84,203,244],"methods,":[64],"it":[65],"easy":[67],"lead":[69],"overfitting":[71],"model":[73,226,250,278],"training.":[74],"To":[75],"address":[76,221],"this":[77,222],"challenge,":[78],"we":[79,110,153,164,191,208,229],"propose":[80,154,209,230],"a":[81,114,125,166,210,231],"mix-based":[82,201,242],"method,":[85],"Joint":[86,235],"Mixing":[87],"Data":[88],"Augmentation":[89],"(JMDA),":[90],"which":[91,239],"can":[92],"generally":[93],"improve":[94,225],"effectiveness":[96,304],"robustness":[98,306],"various":[100],"skeleton-based":[101,262,314],"algorithms.":[104,317],"In":[105],"terms":[106],"spatial":[108,133],"information,":[109,152],"introduce":[111],"SpatialMix":[112],"(SM),":[113],"method":[115,214],"that":[116],"projects":[117],"original":[119,172],"3D":[120],"discrete":[122],"into":[124,204],"2D":[126],"space.":[127],"Then,":[128],"SM":[129],"mixes":[130],"projected":[132],"between":[135],"two":[136,178],"random":[137,179],"samples":[138,180],"during":[139,181],"training":[141,182,233,286],"process":[142],"achieve":[144,184],"spatial-based":[146],"mixing":[147],"augmentation.":[149,189],"Concerning":[150],"temporal":[151,159,167],"TemporalMix":[155],"(TM).":[156],"Leveraging":[157],"continuity":[160],"data,":[163,174],"perform":[165],"resize":[168],"operation":[169],"then":[176],"merge":[177],"temporal-based":[186],"mixed":[187],"Additionally,":[190],"analyze":[192],"Feature":[194,216],"Mismatch":[195],"(FM)":[196],"problem":[197,223],"caused":[198],"by":[199],"introducing":[200],"Then":[207],"new":[211],"preprocessing":[213],"called":[215],"Alignment":[217],"(FA)":[218],"effectively":[220],"performance.":[227,251],"Moreover,":[228],"novel":[232],"pipeline,":[234],"Training":[236],"Strategy":[237],"(JTS),":[238],"combines":[240],"multiple":[241],"methods":[245],"further":[247],"improvement":[248],"Specifically,":[252],"our":[253],"proposed":[254,309],"JMDA":[255,273,310],"plug-and-play":[257],"widely":[259],"applicable":[260],"models.":[265],"At":[266],"same":[268],"time,":[269],"application":[271],"does":[274],"not":[275],"increase":[276],"parameters":[279],"there":[281],"almost":[283],"no":[284],"additional":[285],"cost.":[287],"We":[288],"conduct":[289],"extensive":[290],"experiments":[291],"NTU":[293,297],"RGB+D":[294,298],"60":[295],"120":[299],"datasets":[300],"demonstrate":[302],"several":[312],"mainstream":[313]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}