{"id":"https://openalex.org/W4321786075","doi":"https://doi.org/10.1145/3585388","title":"TEVL: Trilinear Encoder for Video-language Representation Learning","display_name":"TEVL: Trilinear Encoder for Video-language Representation Learning","publication_year":2023,"publication_date":"2023-02-24","ids":{"openalex":"https://openalex.org/W4321786075","doi":"https://doi.org/10.1145/3585388"},"language":"en","primary_location":{"id":"doi:10.1145/3585388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3585388","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059569260","display_name":"Xin Man","orcid":"https://orcid.org/0000-0001-9684-4424"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Man","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643582","display_name":"Feiyu Chen","orcid":"https://orcid.org/0000-0002-0928-6899"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China, China Intelligent Terminal Key Laboratory of Sichuan Province, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China Intelligent Terminal Key Laboratory of Sichuan Province, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621292","display_name":"Mingxing Zhang","orcid":"https://orcid.org/0000-0001-9939-158X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxing Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, China Sichuan Artificial Intelligence Research Institute, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China Sichuan Artificial Intelligence Research Institute, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, China Sichuan Artificial Intelligence Research Institute, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China Sichuan Artificial Intelligence Research Institute, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059569260"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.8425,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7410294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":"5s","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9950000047683716,"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":0.8999167680740356},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8147944211959839},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7557654976844788},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6258238554000854},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5821946263313293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5127049684524536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5108163356781006},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49823975563049316},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4499281346797943},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43208327889442444},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4296093285083771},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4245033264160156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3773956894874573},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10195636749267578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8999167680740356},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8147944211959839},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7557654976844788},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6258238554000854},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5821946263313293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5127049684524536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5108163356781006},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49823975563049316},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4499281346797943},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43208327889442444},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4296093285083771},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4245033264160156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3773956894874573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10195636749267578},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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:10.1145/3585388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3585388","pdf_url":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7153800513","display_name":null,"funder_award_id":"61832001, 62276047","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2249069931","https://openalex.org/W2259472270","https://openalex.org/W2277195237","https://openalex.org/W2398104528","https://openalex.org/W2525778437","https://openalex.org/W2541443726","https://openalex.org/W2547411571","https://openalex.org/W2550936021","https://openalex.org/W2552002300","https://openalex.org/W2619947201","https://openalex.org/W2832876791","https://openalex.org/W2949178656","https://openalex.org/W2952372688","https://openalex.org/W2963351113","https://openalex.org/W2963541336","https://openalex.org/W2963758027","https://openalex.org/W2963954913","https://openalex.org/W2964345792","https://openalex.org/W2965373594","https://openalex.org/W2968124245","https://openalex.org/W2969127500","https://openalex.org/W2970231061","https://openalex.org/W2971207485","https://openalex.org/W2978223337","https://openalex.org/W2981694290","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2990503944","https://openalex.org/W2998356391","https://openalex.org/W3034188691","https://openalex.org/W3034425145","https://openalex.org/W3035119608","https://openalex.org/W3035265375","https://openalex.org/W3048782180","https://openalex.org/W3090449556","https://openalex.org/W3104862079","https://openalex.org/W3105232955","https://openalex.org/W3105858579","https://openalex.org/W3162529291","https://openalex.org/W3162552392","https://openalex.org/W3167366812","https://openalex.org/W3173220247","https://openalex.org/W3187532107","https://openalex.org/W3188030217","https://openalex.org/W3203592524","https://openalex.org/W3207060277","https://openalex.org/W3207072950","https://openalex.org/W3209229003","https://openalex.org/W3217340782","https://openalex.org/W4210871970","https://openalex.org/W4211053420","https://openalex.org/W4212804468","https://openalex.org/W4214553437","https://openalex.org/W4285345750","https://openalex.org/W4287690189","https://openalex.org/W4295036294","https://openalex.org/W4304092583","https://openalex.org/W4304098906","https://openalex.org/W4313887138","https://openalex.org/W6779786894","https://openalex.org/W6802620464","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Pre-training":[0],"model":[1],"on":[2,83,170,194],"large-scale":[3],"unlabeled":[4],"web":[5],"videos":[6,31],"followed":[7],"by":[8],"task-specific":[9],"fine-tuning":[10],"is":[11,151,215],"a":[12,106,118,123,141,147],"canonical":[13],"approach":[14],"to":[15,154],"learning":[16],"video":[17,200,202,209],"and":[18,44,60,88,91,104,121,146,173,190,210],"language":[19,48,61,89,211],"representations.":[20],"However,":[21],"the":[22,47,52,74,84,93,171],"accompanying":[23],"Automatic":[24],"Speech":[25],"Recognition":[26],"(ASR)":[27],"transcripts":[28],"in":[29],"these":[30,102],"are":[32,70],"directly":[33],"transcribed":[34],"from":[35],"audio,":[36],"which":[37,69,159],"may":[38],"be":[39],"inconsistent":[40],"with":[41,176],"visual":[42,59],"information":[43],"would":[45],"impair":[46],"modeling":[49,94],"ability":[50],"of":[51,95],"model.":[53],"Meanwhile,":[54],"previous":[55],"V-L":[56,79],"models":[57],"fuse":[58],"modality":[62],"features":[63],"using":[64],"single-":[65],"or":[66],"dual-stream":[67],"architectures,":[68],"not":[71],"suitable":[72],"for":[73,132],"current":[75],"situation.":[76],"Besides,":[77],"traditional":[78],"research":[80],"focuses":[81],"mainly":[82],"interaction":[85,127],"between":[86],"vision":[87],"modalities":[90,98],"leaves":[92],"relationships":[96],"within":[97],"untouched.":[99],"To":[100],"address":[101],"issues":[103],"maintain":[105],"small":[107],"manual":[108],"labor":[109],"cost,":[110],"we":[111],"add":[112],"automatically":[113],"extracted":[114],"dense":[115],"captions":[116],"as":[117,206,208],"supplementary":[119],"text":[120],"propose":[122],"new":[124],"trilinear":[125],"video-language":[126],"framework":[128],"TEVL":[129,136,169,184],"(Trilinear":[130],"Encoder":[131],"Video-Language":[133],"representation":[134,189],"learning).":[135],"contains":[137],"three":[138,195],"unimodal":[139],"encoders,":[140],"TRIlinear":[142],"encOder":[143],"(TRIO)":[144],"block,":[145],"temporal":[148],"Transformer.":[149],"TRIO":[150],"specially":[152],"designed":[153],"support":[155],"effective":[156],"text-vision-text":[157],"interaction,":[158],"encourages":[160],"inter-modal":[161],"cooperation":[162],"while":[163],"maintaining":[164],"intra-modal":[165],"dependencies.":[166],"We":[167],"pre-train":[168],"HowTo100M":[172],"TV":[174],"datasets":[175],"four":[177],"task":[178],"objectives.":[179],"Experimental":[180],"results":[181],"demonstrate":[182],"that":[183],"can":[185],"learn":[186],"powerful":[187],"video-text":[188],"achieve":[191],"competitive":[192],"performance":[193],"downstream":[196],"tasks,":[197],"including":[198],"multimodal":[199],"captioning,":[201],"Question":[203],"Answering":[204],"(QA),":[205],"well":[207],"inference.":[212],"Implementation":[213],"code":[214],"available":[216],"at":[217],"https://github.com/Gufrannn/TEVL":[218],".":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}