{"id":"https://openalex.org/W3034427277","doi":"https://doi.org/10.1109/icme46284.2020.9102724","title":"Multi-Task Learning of Generalizable Representations for Video Action Recognition","display_name":"Multi-Task Learning of Generalizable Representations for Video Action Recognition","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3034427277","doi":"https://doi.org/10.1109/icme46284.2020.9102724","mag":"3034427277"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5049776517","display_name":"Zhiyu Yao","orcid":"https://orcid.org/0000-0003-2763-7653"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyu Yao","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713555","display_name":"Yunbo Wang","orcid":"https://orcid.org/0000-0002-6224-2481"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Wang","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019241553","display_name":"Mingsheng Long","orcid":"https://orcid.org/0000-0001-9421-463X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Long","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373517","display_name":"Jianmin Wang","orcid":"https://orcid.org/0000-0001-6841-7943"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Wang","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100429010","display_name":"Jiaguang Sun","orcid":"https://orcid.org/0000-0002-5884-7939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaguang Sun","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049776517"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3908,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60909458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9975000023841858,"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993577718734741},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.74541175365448},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6772370338439941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6465637683868408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5656120181083679},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5636399984359741},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.515670657157898},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49236953258514404},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.467029333114624},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45946574211120605},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45632481575012207},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42341309785842896},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4159102439880371},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3508424162864685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33939430117607117},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14180123805999756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993577718734741},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.74541175365448},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6772370338439941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6465637683868408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5656120181083679},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5636399984359741},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.515670657157898},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49236953258514404},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.467029333114624},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45946574211120605},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45632481575012207},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42341309785842896},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4159102439880371},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3508424162864685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33939430117607117},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14180123805999756},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme46284.2020.9102724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W764651262","https://openalex.org/W1522734439","https://openalex.org/W1578985305","https://openalex.org/W1882958252","https://openalex.org/W1983364832","https://openalex.org/W2126579184","https://openalex.org/W2156303437","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2548527721","https://openalex.org/W2566769621","https://openalex.org/W2619947201","https://openalex.org/W2736596806","https://openalex.org/W2778191445","https://openalex.org/W2883429621","https://openalex.org/W2963091558","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963775820","https://openalex.org/W2963820951","https://openalex.org/W2963826681","https://openalex.org/W2964094092","https://openalex.org/W2981385151","https://openalex.org/W2990152177","https://openalex.org/W6600983433","https://openalex.org/W6639480849","https://openalex.org/W6682864246","https://openalex.org/W6752764193","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"In":[0],"classic":[1,190],"video":[2,14,51,77,90],"action":[3,191],"recognition,":[4],"labels":[5],"may":[6,30],"not":[7],"contain":[8],"enough":[9],"information":[10],"about":[11],"the":[12,25,45,65,72,102,116,121,125,147,153,172,175,189,202],"diverse":[13],"appearance":[15],"and":[16,100,124,134,152],"dynamics,":[17],"thus,":[18],"existing":[19],"models":[20,38],"that":[21,63],"are":[22],"trained":[23],"under":[24,39],"standard":[26],"supervised":[27],"learning":[28,87],"paradigm":[29,88],"extract":[31],"less":[32],"generalizable":[33],"features.":[34],"We":[35,61],"evaluate":[36],"these":[37,81],"a":[40,85,159,179,197],"cross-dataset":[41,203],"experiment":[42],"setting,":[43],"as":[44,68,108,131,139],"above":[46],"label":[47,98],"bias":[48,99],"problem":[49],"in":[50,178,201],"analysis":[52],"is":[53,95,183],"even":[54],"more":[55],"prominent":[56],"across":[57],"different":[58],"data":[59,107],"sources.":[60],"find":[62],"using":[64],"optical":[66,122],"flows":[67,123],"model":[69,138],"inputs":[70],"harms":[71],"generalization":[73,103,199],"ability":[74,104,200],"of":[75,174],"most":[76],"recognition":[78,192],"models.Based":[79],"on":[80,115,188],"findings,":[82],"we":[83,119,145],"present":[84],"multi-task":[86,176],"for":[89],"classification.":[91],"Our":[92],"key":[93],"idea":[94],"to":[96,163,185],"avoid":[97],"improve":[101],"by":[105,128,157],"taking":[106,129],"its":[109],"own":[110],"supervision":[111],"or":[112],"supervising":[113],"constraints":[114,171],"data.":[117],"First,":[118],"take":[120],"RGB":[126],"frames":[127],"them":[130],"auxiliary":[132,148],"supervisions,":[133],"thus":[135],"naming":[136],"our":[137],"Reversed":[140],"Two-Stream":[141],"Networks":[142],"(Rev2Net).":[143],"Further,":[144],"collaborate":[146],"flow":[149],"prediction":[150],"task":[151,156],"frame":[154],"reconstruction":[155],"introducing":[158],"new":[160],"training":[161],"objective":[162],"Rev2Net,":[164],"named":[165],"Decoding":[166],"Discrepancy":[167],"Penalty":[168],"(DDP),":[169],"which":[170],"discrepancy":[173],"features":[177],"self-supervised":[180],"manner.":[181],"Rev2Net":[182],"shown":[184],"be":[186],"effective":[187],"task.":[193],"It":[194],"specifically":[195],"shows":[196],"strong":[198],"experiments.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}