{"id":"https://openalex.org/W4388191389","doi":"https://doi.org/10.1145/3581783.3612496","title":"Data-Efficient Masked Video Modeling for Self-supervised Action Recognition","display_name":"Data-Efficient Masked Video Modeling for Self-supervised Action Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388191389","doi":"https://doi.org/10.1145/3581783.3612496"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5101431986","display_name":"Qiankun Li","orcid":"https://orcid.org/0000-0001-5121-1682"},"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiankun Li","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5121-1682","affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008207535","display_name":"Xiaolong Huang","orcid":"https://orcid.org/0009-0005-5502-2535"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Huang","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0005-5502-2535","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087412143","display_name":"Zhifan Wan","orcid":"https://orcid.org/0009-0009-2742-3613"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifan Wan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-2742-3613","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016105630","display_name":"Lanqing Hu","orcid":"https://orcid.org/0000-0002-8788-5811"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanqing Hu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8788-5811","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068510937","display_name":"Shuzhe Wu","orcid":"https://orcid.org/0000-0002-4455-4123"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhe Wu","raw_affiliation_strings":["Beijing Huawei Cloud Computing Technologies Co., Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4455-4123","affiliations":[{"raw_affiliation_string":"Beijing Huawei Cloud Computing Technologies Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010618416","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-8899-3996"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8899-3996","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297728","display_name":"Shiguang Shan","orcid":"https://orcid.org/0000-0002-8348-392X"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguang Shan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8348-392X","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1859-900X","affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2723","last_page":"2733"},"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":0.9990000128746033,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8710030913352966},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6547061204910278},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6339247226715088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6187729835510254},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5371962189674377},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5030097365379333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46548381447792053},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4240856468677521},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42371347546577454},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12418004870414734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8710030913352966},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6547061204910278},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6339247226715088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187729835510254},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5371962189674377},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5030097365379333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46548381447792053},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4240856468677521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42371347546577454},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12418004870414734},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3287433136","display_name":null,"funder_award_id":"62176251, 61976219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"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":39,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2093488518","https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2161969291","https://openalex.org/W2558661413","https://openalex.org/W2625366777","https://openalex.org/W2963524571","https://openalex.org/W2963563276","https://openalex.org/W2963631366","https://openalex.org/W2981689412","https://openalex.org/W2981774933","https://openalex.org/W2984008963","https://openalex.org/W2997907976","https://openalex.org/W3034381931","https://openalex.org/W3037309139","https://openalex.org/W3094454579","https://openalex.org/W3110190397","https://openalex.org/W3123599388","https://openalex.org/W3129409502","https://openalex.org/W3133964188","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3174331338","https://openalex.org/W3197113684","https://openalex.org/W3202721444","https://openalex.org/W3204588463","https://openalex.org/W3216270236","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4280490805","https://openalex.org/W4281249524","https://openalex.org/W4292794848","https://openalex.org/W4304091718","https://openalex.org/W4304091966","https://openalex.org/W4304092138","https://openalex.org/W4312312750","https://openalex.org/W4312560592","https://openalex.org/W4313156423"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W3095877357","https://openalex.org/W183202219","https://openalex.org/W10861731","https://openalex.org/W2072565696","https://openalex.org/W2050451745"],"abstract_inverted_index":{"Recently,":[0],"self-supervised":[1,81],"video":[2,26,131],"representation":[3],"learning":[4,99],"based":[5,115],"on":[6,103,116,170,203],"Masked":[7,76],"Video":[8,77],"Modeling":[9,78],"(MVM)":[10],"has":[11],"demonstrated":[12],"promising":[13],"results":[14],"for":[15,80],"action":[16,82,187],"recognition.":[17,83],"However,":[18],"existing":[19],"methods":[20],"face":[21],"two":[22],"significant":[23,55],"challenges:":[24],"(1)":[25],"actions":[27,213],"involve":[28],"a":[29,71,85,129],"crucial":[30],"temporal":[31,106,138],"dimension,":[32],"yet":[33],"current":[34],"masking":[35,87,111,122],"strategies":[36,148],"adopt":[37],"inefficient":[38],"random":[39],"approaches":[40],"that":[41,178,208],"undermine":[42],"low-density":[43],"dynamic":[44,113],"motion":[45],"clues":[46],"in":[47,184,215],"videos;":[48],"(2)":[49],"pre-training":[50],"requires":[51],"large-scale":[52],"datasets":[53],"and":[54,62,145,175,194],"computing":[56],"resources":[57],"(including":[58],"large":[59],"batch":[60],"sizes":[61],"enormous":[63],"iterations).":[64],"To":[65],"address":[66],"these":[67],"issues,":[68],"we":[69],"propose":[70],"novel":[72,86],"method":[73,180],"named":[74,89],"Data-Efficient":[75],"(DEMVM)":[79],"Specifically,":[84],"strategy":[88],"Flow-Guided":[90],"Dense":[91],"Masking":[92,142],"(FGDM)":[93],"is":[94],"proposed":[95],"to":[96,112,123,133,151,155,157],"facilitate":[97],"efficient":[98,192],"by":[100],"focusing":[101],"more":[102],"the":[104,135,153,158,161,185,200,204,216],"action-related":[105],"clues,":[107],"which":[108],"applies":[109],"dense":[110],"regions":[114],"optical":[117],"flow":[118],"priors,":[119],"while":[120],"sparse":[121],"background":[124],"regions.":[125],"Furthermore,":[126],"DEMVM":[127,209],"introduces":[128],"3D":[130],"tokenizer":[132],"enhance":[134],"modeling":[136],"of":[137,160,218],"clues.":[139],"Finally,":[140],"Progressive":[141],"Ratio":[143],"(PMR)":[144],"2D":[146],"initialization":[147],"are":[149],"presented":[150],"enable":[152],"model":[154],"adapt":[156],"characteristics":[159],"MVM":[162],"paradigm":[163],"during":[164],"different":[165],"training":[166],"stages.":[167],"Extensive":[168],"experiments":[169],"multiple":[171],"benchmarks,":[172],"UCF101,":[173],"HMDB51,":[174],"Mimetics,":[176],"demonstrate":[177],"our":[179],"achieves":[181],"state-of-the-art":[182],"performance":[183],"downstream":[186],"recognition":[188],"task":[189],"with":[190],"both":[191],"data":[193],"low":[195],"computational":[196],"cost.":[197],"More":[198],"interestingly,":[199],"few-shot":[201],"experiment":[202],"Mimetics":[205],"dataset":[206],"shows":[207],"can":[210],"accurately":[211],"recognize":[212],"even":[214],"presence":[217],"context":[219],"bias.":[220]},"counts_by_year":[{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}