{"id":"https://openalex.org/W2949178656","doi":null,"title":"Contrastive Bidirectional Transformer for Temporal Representation Learning","display_name":"Contrastive Bidirectional Transformer for Temporal Representation Learning","publication_year":2019,"publication_date":"2019-06-13","ids":{"openalex":"https://openalex.org/W2949178656","mag":"2949178656"},"language":"en","primary_location":{"id":"mag:2949178656","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/corr/corr1906.html#abs-1906-05743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5100722234","display_name":"Chen Sun","orcid":"https://orcid.org/0000-0001-8772-9627","observed_orcids":["https://orcid.org/0000-0001-8772-9627","https://orcid.org/0000-0002-3036-7212"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081673327","display_name":"Fabien Baradel","orcid":"https://orcid.org/0000-0003-4625-1713","observed_orcids":["https://orcid.org/0000-0003-4625-1713"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabien Baradel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002713363","display_name":"Kevin P. Murphy","orcid":"https://orcid.org/0000-0001-5196-7236","observed_orcids":["https://orcid.org/0000-0001-5196-7236"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Murphy","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5196-7236","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":"https://orcid.org/0009-0005-7239-3741","observed_orcids":["https://orcid.org/0009-0005-7239-3741"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8308,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":{"value":0.9885561,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8291000127792358,"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":0.8291000127792358,"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":0.11779999732971191,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.01860000006854534,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/contrastive-learning","display_name":"contrastive learning","score":0.7590000033378601},{"id":"https://openalex.org/keywords/bidirectional-transformer","display_name":"bidirectional transformer","score":0.9240000247955322},{"id":"https://openalex.org/keywords/temporal-representation-learning","display_name":"temporal representation learning","score":0.9909999966621399},{"id":"https://openalex.org/keywords/mutual-information-maximization","display_name":"mutual information maximization","score":0.8500000238418579},{"id":"https://openalex.org/keywords/visual-features","display_name":"visual features","score":0.44999998807907104},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.6460000276565552},{"id":"https://openalex.org/keywords/action-prediction","display_name":"action prediction","score":0.9890000224113464},{"id":"https://openalex.org/keywords/video-modeling","display_name":"video modeling","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.804794430732727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364267110824585},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6588375568389893},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5412340760231018},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5101228356361389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4769127070903778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44578683376312256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3670170307159424},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.18528228998184204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08983871340751648},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2949178656","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/corr/corr1906.html#abs-1906-05743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1566289585","https://openalex.org/W2056120433","https://openalex.org/W2099614498","https://openalex.org/W2109698606","https://openalex.org/W2126579184","https://openalex.org/W2152790380","https://openalex.org/W2156303437","https://openalex.org/W2185243164","https://openalex.org/W2196697617","https://openalex.org/W2235034809","https://openalex.org/W2422305492","https://openalex.org/W2511428026","https://openalex.org/W2618799552","https://openalex.org/W2619082050","https://openalex.org/W2626778328","https://openalex.org/W2773514261","https://openalex.org/W2778816415","https://openalex.org/W2787560479","https://openalex.org/W2795410839","https://openalex.org/W2803088946","https://openalex.org/W2887997457","https://openalex.org/W2941818575","https://openalex.org/W2949099979","https://openalex.org/W2952132648","https://openalex.org/W2955874753","https://openalex.org/W2962688385","https://openalex.org/W2962756039","https://openalex.org/W2962865004","https://openalex.org/W2963341956","https://openalex.org/W2963351113","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W2975357369","https://openalex.org/W4313009245","https://openalex.org/W3217557337","https://openalex.org/W4386083157","https://openalex.org/W4224920427","https://openalex.org/W4400115185","https://openalex.org/W4313305652","https://openalex.org/W7018339548","https://openalex.org/W3123599388","https://openalex.org/W4386172434"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"at":[3,81,86],"learning":[4],"representations":[5,120],"for":[6,21,125],"long":[7,122],"sequences":[8,23,77,124],"of":[9,19,24,117,152],"continuous\nsignals.":[10],"Recently,":[11],"the":[12,17,35,45,52,59,71,82,87,101,104,115,118,150,153],"BERT":[13],"model":[14,60],"has":[15],"demonstrated":[16],"effectiveness":[18,116],"stacked\ntransformers":[20],"representing":[22],"discrete":[25],"signals":[26],"(i.e.":[27],"word":[28],"tokens).\nInspired":[29],"by":[30,138],"its":[31,40],"success,":[32],"we":[33,93,147],"adopt":[34],"stacked":[36],"transformer":[37],"architecture,":[38],"but\ngeneralize":[39],"training":[41],"objective":[42],"to":[43,61,95,99,137],"maximize":[44],"mutual":[46],"information":[47],"between\nthe":[48],"masked":[49],"signals,":[50,64],"and":[51,90,128],"bidirectional":[53],"context,":[54],"via":[55,111],"contrastive":[56],"loss.":[57],"This\nenables":[58],"handle":[62],"continuous":[63],"such":[65],"as":[66],"visual":[67],"features.":[68],"We\nfurther":[69],"consider":[70],"case":[72],"when":[73],"there":[74],"are":[75],"multiple":[76],"that":[78,133],"are\nsemantically":[79],"aligned":[80],"sequence-level":[83],"but":[84],"not":[85],"element-level":[88],"(e.g.\nvideo":[89],"ASR),":[91],"where":[92],"propose":[94],"use":[96],"a":[97],"Transformer":[98],"estimate":[100],"mutual\ninformation":[102],"between":[103],"two":[105],"sequences,":[106],"which":[107],"is":[108],"again":[109],"maximized":[110],"contrastive\nloss.":[112],"We":[113],"demonstrate":[114],"learned":[119],"on\nmodeling":[121],"video":[123,129],"action":[126],"anticipation":[127],"captioning.":[130],"The\nresults":[131],"show":[132],"our":[134],"method,":[135],"referred":[136],"Contrastive":[139],"Bidirectional\nTransformer":[140],"({\\bf":[141],"CBT}),":[142],"outperforms":[143],"various":[144],"baselines":[145],"significantly.\nFurthermore,":[146],"improve":[148],"over":[149],"state":[151],"art.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":45},{"year":2019,"cited_by_count":8}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-06-27T00:00:00"}