{"id":"https://openalex.org/W2735673432","doi":"https://doi.org/10.1109/tmm.2017.2722687","title":"VideoWhisper: Toward Discriminative Unsupervised Video Feature Learning With Attention-Based Recurrent Neural Networks","display_name":"VideoWhisper: Toward Discriminative Unsupervised Video Feature Learning With Attention-Based Recurrent Neural Networks","publication_year":2017,"publication_date":"2017-07-11","ids":{"openalex":"https://openalex.org/W2735673432","doi":"https://doi.org/10.1109/tmm.2017.2722687","mag":"2735673432"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2017.2722687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2017.2722687","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5101887026","display_name":"Na Zhao","orcid":"https://orcid.org/0000-0003-2329-7014"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Na Zhao","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101887026"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.0012,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.85053312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"19","issue":"9","first_page":"2080","last_page":"2092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8540603518486023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7332246899604797},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6739997863769531},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6615095734596252},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.6035546660423279},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5826951265335083},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5471370220184326},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.540280818939209},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5369598269462585},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44898608326911926},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44712692499160767},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4458421766757965},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4443161189556122},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43940433859825134},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41569894552230835},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38089051842689514},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3134593963623047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540603518486023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7332246899604797},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6739997863769531},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6615095734596252},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6035546660423279},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5826951265335083},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5471370220184326},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.540280818939209},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5369598269462585},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44898608326911926},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44712692499160767},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4458421766757965},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4443161189556122},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43940433859825134},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41569894552230835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38089051842689514},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3134593963623047},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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:10.1109/tmm.2017.2722687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2017.2722687","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W180242331","https://openalex.org/W1483393862","https://openalex.org/W1513753641","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1544092585","https://openalex.org/W1568514080","https://openalex.org/W1599220855","https://openalex.org/W1686810756","https://openalex.org/W1777628566","https://openalex.org/W1923211482","https://openalex.org/W1923404803","https://openalex.org/W1947481528","https://openalex.org/W1950136256","https://openalex.org/W1966385142","https://openalex.org/W2005763119","https://openalex.org/W2012592962","https://openalex.org/W2016053056","https://openalex.org/W2020163092","https://openalex.org/W2025432722","https://openalex.org/W2027922120","https://openalex.org/W2043220995","https://openalex.org/W2064675550","https://openalex.org/W2105101328","https://openalex.org/W2116435618","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2156303437","https://openalex.org/W2157331557","https://openalex.org/W2161565164","https://openalex.org/W2163455955","https://openalex.org/W2336920772","https://openalex.org/W2520610372","https://openalex.org/W2591644541","https://openalex.org/W2751429626","https://openalex.org/W2951183276","https://openalex.org/W2962826786","https://openalex.org/W3099884890","https://openalex.org/W4294306266","https://openalex.org/W6630841690","https://openalex.org/W6630875275","https://openalex.org/W6632527360","https://openalex.org/W6634221342","https://openalex.org/W6637373629","https://openalex.org/W6677326919","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682864246","https://openalex.org/W6734771144"],"related_works":["https://openalex.org/W3174759195","https://openalex.org/W3167013339","https://openalex.org/W4287121366","https://openalex.org/W2597948870","https://openalex.org/W2428505524","https://openalex.org/W2962722950","https://openalex.org/W60493759","https://openalex.org/W3213069564","https://openalex.org/W4308619659","https://openalex.org/W4389072551"],"abstract_inverted_index":{"We":[0,142],"present":[1],"VideoWhisper,":[2],"a":[3,24,39,67,80,86],"novel":[4,68],"approach":[5],"for":[6,74],"unsupervised":[7,47],"video":[8,25,43,48,69,76,102,148,159,164,179],"representation":[9,149,165],"learning.":[10],"Based":[11],"on":[12,53,156],"the":[13,16,20,34,98,101,127,137,151],"observation":[14],"that":[15,57,163],"frame":[17,35],"sequence":[18,87,129],"encodes":[19],"temporal":[21,138],"dynamics":[22],"of":[23,88,140],"(e.g.,":[26],"object":[27],"movement":[28],"and":[29,130,181],"event":[30,182],"evolution),":[31],"we":[32,78,107,161],"treat":[33],"sequential":[36],"order":[37],"as":[38,97,110,178],"self-supervision":[40],"to":[41,60,84,125,135,146,172],"learn":[42,136],"representations.":[44],"Unlike":[45],"other":[46],"feature":[49,55],"learning":[50,71,114],"methods":[51],"based":[52],"frame-level":[54],"reconstruction":[56],"is":[58,64,123,133,170],"sensitive":[59],"visual":[61,82],"variance,":[62],"VideoWhisper":[63,109],"driven":[65],"by":[66,167],"\u201csequence-to-whisper\u201d":[70],"strategy.":[72],"Specifically,":[73],"each":[75],"sequence,":[77],"use":[79],"prelearned":[81],"dictionary":[83],"generate":[85,147],"high-level":[89],"semantics,":[90],"dubbed":[91],"\u201cwhisper,\u201d":[92],"which":[93],"can":[94],"be":[95],"considered":[96],"language":[99],"describing":[100],"dynamics.":[103],"In":[104],"this":[105],"way,":[106],"model":[108,115,122],"an":[111],"end-to-end":[112],"sequence-to-sequence":[113],"using":[116],"attention-based":[117],"recurrent":[118],"neural":[119],"networks.":[120],"This":[121],"trained":[124],"predict":[126],"whisper":[128],"hence":[131],"it":[132],"able":[134],"structure":[139],"videos.":[141],"propose":[143],"two":[144,157],"ways":[145],"from":[150],"model.":[152],"Through":[153],"extensive":[154],"experiments":[155],"real-world":[158],"datasets,":[160],"demonstrate":[162],"learned":[166],"V":[168],"ideoWhisper":[169],"effective":[171],"boost":[173],"fundamental":[174],"multimedia":[175],"applications":[176],"such":[177],"retrieval":[180],"classification.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}