{"id":"https://openalex.org/W4390874103","doi":"https://doi.org/10.1109/iccv51070.2023.01876","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","display_name":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390874103","doi":"https://doi.org/10.1109/iccv51070.2023.01876"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.01876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.01876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5016619434","display_name":"Andong Deng","orcid":"https://orcid.org/0000-0002-5606-4463"},"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":"Andong Deng","raw_affiliation_strings":["University of Central Florida,Center for Research in Computer Vision,USA","Center for Research in Computer Vision, University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Center for Research in Computer Vision,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009793780","display_name":"Taojiannan Yang","orcid":"https://orcid.org/0000-0001-8564-9439"},"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":"Taojiannan Yang","raw_affiliation_strings":["University of Central Florida,Center for Research in Computer Vision,USA","Center for Research in Computer Vision, University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Center for Research in Computer Vision,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","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":["University of Central Florida,Center for Research in Computer Vision,USA","Center for Research in Computer Vision, University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Center for Research in Computer Vision,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20462","last_page":"20474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9908999800682068,"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":0.9896000027656555,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8573810458183289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8283903002738953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6330199837684631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6140322089195251},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6072706580162048},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4695470929145813},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4553864002227783},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4496583640575409},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4450942277908325},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4395732581615448},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4221356511116028},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41534435749053955}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8573810458183289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283903002738953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6330199837684631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6140322089195251},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6072706580162048},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4695470929145813},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4553864002227783},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4496583640575409},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4450942277908325},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4395732581615448},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4221356511116028},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41534435749053955},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51070.2023.01876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.01876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":101,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W2016053056","https://openalex.org/W2019660985","https://openalex.org/W2126579184","https://openalex.org/W2156303437","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2798963049","https://openalex.org/W2799176631","https://openalex.org/W2883429621","https://openalex.org/W2887051120","https://openalex.org/W2939059980","https://openalex.org/W2961193895","https://openalex.org/W2962778061","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W2963820951","https://openalex.org/W2963886665","https://openalex.org/W2964037671","https://openalex.org/W2964094654","https://openalex.org/W2980287048","https://openalex.org/W2981923053","https://openalex.org/W2987427063","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2994508843","https://openalex.org/W3007751154","https://openalex.org/W3009828227","https://openalex.org/W3010010212","https://openalex.org/W3010874390","https://openalex.org/W3012362498","https://openalex.org/W3034572008","https://openalex.org/W3034630387","https://openalex.org/W3035180180","https://openalex.org/W3089682612","https://openalex.org/W3090204015","https://openalex.org/W3094454579","https://openalex.org/W3094502228","https://openalex.org/W3119437694","https://openalex.org/W3126721948","https://openalex.org/W3138516171","https://openalex.org/W3145385912","https://openalex.org/W3170837227","https://openalex.org/W3173354537","https://openalex.org/W3174053790","https://openalex.org/W3174568846","https://openalex.org/W3176780013","https://openalex.org/W3200114289","https://openalex.org/W3202679759","https://openalex.org/W3205711766","https://openalex.org/W3205786327","https://openalex.org/W3208431284","https://openalex.org/W3213875247","https://openalex.org/W4214516465","https://openalex.org/W4214612132","https://openalex.org/W4221167396","https://openalex.org/W4224246420","https://openalex.org/W4225112599","https://openalex.org/W4226196786","https://openalex.org/W4280490805","https://openalex.org/W4285175079","https://openalex.org/W4312266966","https://openalex.org/W4312365371","https://openalex.org/W4312443924","https://openalex.org/W4312560592","https://openalex.org/W4312769057","https://openalex.org/W4312956471","https://openalex.org/W4376312579","https://openalex.org/W4382467086","https://openalex.org/W4384519142","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6637373629","https://openalex.org/W6639480849","https://openalex.org/W6682864246","https://openalex.org/W6739901393","https://openalex.org/W6749916090","https://openalex.org/W6750355821","https://openalex.org/W6754337694","https://openalex.org/W6765307894","https://openalex.org/W6784333009","https://openalex.org/W6784660784","https://openalex.org/W6790307280","https://openalex.org/W6791353385","https://openalex.org/W6801520322","https://openalex.org/W6801567822","https://openalex.org/W6802870958","https://openalex.org/W6803023527","https://openalex.org/W6810039040","https://openalex.org/W6810265253","https://openalex.org/W6810561866","https://openalex.org/W6838789689","https://openalex.org/W6849878650","https://openalex.org/W6852932568","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4379115841","https://openalex.org/W2083794993","https://openalex.org/W1511772879","https://openalex.org/W4394660363","https://openalex.org/W2186315912","https://openalex.org/W2248125223","https://openalex.org/W2588591308","https://openalex.org/W2910542634","https://openalex.org/W2127898439","https://openalex.org/W3082894236"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,7,23,34,50,68,87],"building":[3,155],"a":[4,12,24,57,66,84,145],"benchmark":[5,150],"(suite":[6],"datasets)":[8],"is":[9,65],"to":[10,42,135,151],"provide":[11],"unified":[13],"protocol":[14],"for":[15],"fair":[16,146],"evaluation":[17,149],"and":[18,80,103,116,138,147,162],"thus":[19],"facilitate":[20],"the":[21,48,124],"evolution":[22],"specific":[25],"area.":[26],"Nonetheless,":[27],"we":[28,54,92,139],"point":[29],"out":[30],"that":[31,123],"existing":[32],"protocols":[33],"action":[35],"recognition":[36],"could":[37],"yield":[38],"partial":[39],"evaluations":[40],"due":[41],"several":[43],"limitations.":[44],"To":[45],"comprehensively":[46],"probe":[47],"effectiveness":[49],"spatiotemporal":[51,97,157],"representation":[52],"learning,":[53],"introduce":[55],"BEAR,":[56,91],"new":[58],"BEnchmark":[59],"on":[60,132,154],"video":[61,70],"Action":[62],"Recognition.":[63],"BEAR":[64,141],"collection":[67],"18":[69],"datasets":[71,133],"grouped":[72],"into":[73],"5":[74],"categories":[75],"(anomaly,":[76],"gesture,":[77],"daily,":[78],"sports,":[79],"instructional),":[81],"which":[82],"covers":[83],"diverse":[85],"set":[86],"real-world":[88,136],"applications.":[89],"With":[90],"thoroughly":[93],"evaluate":[94],"6":[95],"common":[96],"models":[98,163],"pre-trained":[99],"by":[100],"both":[101],"supervised":[102],"self-supervised":[104],"learning.":[105],"We":[106],"also":[107],"report":[108],"transfer":[109],"performance":[110,131],"via":[111],"standard":[112],"finetuning,":[113,115],"few-shot":[114],"unsupervised":[117],"domain":[118],"adaptation.":[119],"Our":[120,159],"observation":[121],"suggests":[122],"current":[125],"state-of-the-art":[126],"cannot":[127],"solidly":[128],"guarantee":[129],"high":[130],"close":[134],"applications,":[137],"hope":[140],"can":[142],"serve":[143],"as":[144],"challenging":[148],"gain":[152],"insights":[153],"next-generation":[156],"learners.":[158],"dataset,":[160],"code,":[161],"are":[164],"released":[165],"at:":[166],"https://github.com/AndongDeng/BEAR":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}