{"id":"https://openalex.org/W4361856786","doi":"https://doi.org/10.1109/tmm.2023.3263288","title":"MAR: <u>M</u>asked Autoencoders for Efficient <u>A</u>ction <u>R</u>ecognition","display_name":"MAR: <u>M</u>asked Autoencoders for Efficient <u>A</u>ction <u>R</u>ecognition","publication_year":2023,"publication_date":"2023-03-30","ids":{"openalex":"https://openalex.org/W4361856786","doi":"https://doi.org/10.1109/tmm.2023.3263288"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3263288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3263288","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","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/A5030206792","display_name":"Zhiwu Qing","orcid":"https://orcid.org/0000-0002-4776-357X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiwu Qing","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4776-357X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449697","display_name":"Shiwei Zhang","orcid":"https://orcid.org/0000-0002-6929-5295"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwei Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-6929-5295","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075562531","display_name":"Ziyuan Huang","orcid":"https://orcid.org/0000-0002-4544-0427"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziyuan Huang","raw_affiliation_strings":["Advanced Robotics Centre, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4544-0427","affiliations":[{"raw_affiliation_string":"Advanced Robotics Centre, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068095485","display_name":"Xiang Wang","orcid":"https://orcid.org/0000-0003-0785-3367"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0785-3367","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030517812","display_name":"Yuehuan Wang","orcid":"https://orcid.org/0000-0001-7046-7587"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehuan Wang","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7046-7587","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016207654","display_name":"Yiliang Lv","orcid":"https://orcid.org/0000-0002-3101-5569"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiliang Lv","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035295689","display_name":"Changxin Gao","orcid":"https://orcid.org/0000-0003-2736-3920"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxin Gao","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-2736-3920","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013734579","display_name":"Nong Sang","orcid":"https://orcid.org/0000-0002-9167-1496"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Sang","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-9167-1496","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5030206792"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":5.5778,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.97115372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"218","last_page":"233"},"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":0.9958999752998352,"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":0.9955000281333923,"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":0.828881025314331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6277446746826172},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5826895236968994},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.43590879440307617},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4179411232471466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40273526310920715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38178303837776184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828881025314331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6277446746826172},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5826895236968994},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.43590879440307617},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4179411232471466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40273526310920715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38178303837776184},{"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:10.1109/tmm.2023.3263288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3263288","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1849468495","display_name":null,"funder_award_id":"U22B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320317417","display_name":"Alibaba DAMO Academy","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":109,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W2025768430","https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2161969291","https://openalex.org/W2183341477","https://openalex.org/W2331143823","https://openalex.org/W2507009361","https://openalex.org/W2619947201","https://openalex.org/W2622263826","https://openalex.org/W2625366777","https://openalex.org/W2752796333","https://openalex.org/W2807968599","https://openalex.org/W2809562466","https://openalex.org/W2883429621","https://openalex.org/W2913950831","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2963526497","https://openalex.org/W2963645879","https://openalex.org/W2963820951","https://openalex.org/W2965373594","https://openalex.org/W2981385151","https://openalex.org/W2984287396","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W2999794487","https://openalex.org/W3004505825","https://openalex.org/W3010010212","https://openalex.org/W3015468748","https://openalex.org/W3034572008","https://openalex.org/W3035141718","https://openalex.org/W3035303837","https://openalex.org/W3035452548","https://openalex.org/W3035682985","https://openalex.org/W3037046522","https://openalex.org/W3046614818","https://openalex.org/W3103366418","https://openalex.org/W3104591054","https://openalex.org/W3107849462","https://openalex.org/W3115964123","https://openalex.org/W3126721948","https://openalex.org/W3128990302","https://openalex.org/W3138516171","https://openalex.org/W3145385912","https://openalex.org/W3156973125","https://openalex.org/W3170837227","https://openalex.org/W3171349866","https://openalex.org/W3173948887","https://openalex.org/W3174751993","https://openalex.org/W3175528717","https://openalex.org/W3181279185","https://openalex.org/W3201942032","https://openalex.org/W3210279979","https://openalex.org/W3216270236","https://openalex.org/W4210915468","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214661601","https://openalex.org/W4214727094","https://openalex.org/W4214747681","https://openalex.org/W4226146163","https://openalex.org/W4281618957","https://openalex.org/W4282964635","https://openalex.org/W4285166085","https://openalex.org/W4312312750","https://openalex.org/W4312560592","https://openalex.org/W4312706062","https://openalex.org/W4312769131","https://openalex.org/W4312800447","https://openalex.org/W4312804044","https://openalex.org/W4313156423","https://openalex.org/W4321609065","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6674330103","https://openalex.org/W6726497184","https://openalex.org/W6739622702","https://openalex.org/W6745136726","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6761472960","https://openalex.org/W6762122294","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6767318615","https://openalex.org/W6773829392","https://openalex.org/W6776048684","https://openalex.org/W6779879114","https://openalex.org/W6784333009","https://openalex.org/W6784660784","https://openalex.org/W6788135285","https://openalex.org/W6790978476","https://openalex.org/W6796761347","https://openalex.org/W6797236868","https://openalex.org/W6797263693","https://openalex.org/W6802521057","https://openalex.org/W6810265253","https://openalex.org/W6810661123","https://openalex.org/W6838789689","https://openalex.org/W6838816370","https://openalex.org/W6840599879","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W4252684102","https://openalex.org/W2608983118","https://openalex.org/W2352307597","https://openalex.org/W1979633005","https://openalex.org/W2163724607","https://openalex.org/W3135403405","https://openalex.org/W2023227762","https://openalex.org/W1980092392","https://openalex.org/W2551337514"],"abstract_inverted_index":{"Standard":[0],"approaches":[1],"for":[2,133,179,186],"video":[3,28],"action":[4],"recognition":[5],"usually":[6],"operate":[7],"on":[8,71,237],"full":[9],"input":[10],"videos,":[11],"which":[12,58],"is":[13,109,252],"inefficient":[14],"due":[15],"to":[16,41,94,98,111,153,228],"the":[17,34,75,96,100,103,113,121,124,141,170,174,182,193,245,258],"widespread":[18],"spatio-temporal":[19,43,114],"redundancy":[20],"in":[21,26,116,131],"videos.":[22,76,117],"The":[23],"recent":[24],"progress":[25],"masked":[27],"modelling,":[29],"specifically":[30],"VideoMAE,":[31],"has":[32],"shown":[33],"ability":[35],"of":[36,66,74,196,248,255,257],"vanilla":[37],"Vision":[38],"Transformers":[39],"(ViT)":[40],"complement":[42],"contexts":[44],"using":[45],"limited":[46],"visual":[47],"content.":[48],"Inspired":[49],"by":[50,62,198,211,223,233],"this,":[51],"we":[52,137,161,216],"propose":[53,162],"Masked":[54],"Action":[55],"Recognition":[56],"(MAR),":[57],"reduces":[59],"redundant":[60],"computation":[61,246],"discarding":[63],"a":[64,72,163,212,219,229],"proportion":[65],"patches":[67,122],"and":[68,87,181,240],"operating":[69],"only":[70,253],"portion":[73],"MAR":[77,190,205,224],"includes":[78],"two":[79],"essential":[80],"components:":[81],"<italic":[82,88],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[83,89,267],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">cell":[84],"running":[85,107],"masking</i>":[86],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">bridging":[90],"classifier</i>":[91],".":[92,269],"Specifically,":[93],"enable":[95],"ViT":[97,175,197,209],"perceive":[99],"details":[101],"beyond":[102],"visible":[104],"patches,":[105,150],"cell":[106],"masking":[108],"used":[110,178,185],"preserve":[112],"correlations":[115],"This":[118],"ensures":[119],"that":[120,166,204,218,256],"at":[123],"same":[125],"spatial":[126],"location":[127],"can":[128,145,167,191],"be":[129],"observed":[130,143],"turn":[132],"easy":[134],"reconstructions.":[135],"Additionally,":[136],"notice":[138],"that,":[139],"although":[140],"partially":[142],"features":[144,177,184],"reconstruct":[146],"semantically":[147],"explicit":[148],"invisible":[149],"they":[151],"fail":[152],"achieve":[154],"accurate":[155],"classification.":[156,187],"To":[157],"address":[158],"this":[159],"issue,":[160],"bridging":[164],"classifier":[165],"help":[168],"fill":[169],"semantic":[171],"gap":[172],"between":[173],"encoded":[176],"reconstruction":[180],"specialized":[183],"Our":[188],"proposed":[189],"reduce":[192],"computational":[194],"cost":[195],"53%.":[199],"Extensive":[200],"experiments":[201],"have":[202,262],"demonstrated":[203],"consistently":[206],"outperforms":[207],"existing":[208],"models":[210],"notable":[213],"margin.":[214],"Notably,":[215],"found":[217],"ViT-Large":[220,250],"model":[221,231,251],"fine-tuned":[222,232],"achieves":[225],"comparable":[226],"performance":[227],"ViT-Huge":[230,259],"standard":[234],"training":[235],"methods":[236],"both":[238],"Kinetics-400":[239],"Something-Something":[241],"v2":[242],"datasets.":[243],"Moreover,":[244],"overhead":[247],"our":[249],"14.5%":[254],"model.":[260],"Codes":[261],"been":[263],"made":[264],"available":[265],"<uri":[266],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/alibaba-mmai-research/Masked-Action-Recognition</uri>":[268]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}