{"id":"https://openalex.org/W2751429626","doi":"https://doi.org/10.1109/icme.2017.8019344","title":"VIDEOWHISPER: Towards unsupervised learning of discriminative features of videos with RNN","display_name":"VIDEOWHISPER: Towards unsupervised learning of discriminative features of videos with RNN","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2751429626","doi":"https://doi.org/10.1109/icme.2017.8019344","mag":"2751429626"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/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"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of 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"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621291","display_name":"Mingxing Zhang","orcid":"https://orcid.org/0000-0001-8363-6968"},"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":"Mingxing Zhang","raw_affiliation_strings":["School of Computing, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of 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"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","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"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","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"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101887026"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.182,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56757489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"277","last_page":"282"},"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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/discriminative-model","display_name":"Discriminative model","score":0.8472669124603271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7638794183731079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6634153127670288},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5907296538352966},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5153583884239197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46574079990386963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41946983337402344},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.098641037940979}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8472669124603271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638794183731079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6634153127670288},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5907296538352966},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5153583884239197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46574079990386963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41946983337402344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.098641037940979}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2017.8019344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7799999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1551279196","https://openalex.org/W1568514080","https://openalex.org/W1686810756","https://openalex.org/W1777628566","https://openalex.org/W1923404803","https://openalex.org/W1950136256","https://openalex.org/W2027922120","https://openalex.org/W2064675550","https://openalex.org/W2105101328","https://openalex.org/W2116435618","https://openalex.org/W2130942839","https://openalex.org/W2139501017","https://openalex.org/W2156303437","https://openalex.org/W2157331557","https://openalex.org/W2163455955","https://openalex.org/W2336920772","https://openalex.org/W2509909094","https://openalex.org/W2515034697","https://openalex.org/W2605350416","https://openalex.org/W4294306266","https://openalex.org/W6679436768","https://openalex.org/W6682864246"],"related_works":["https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427","https://openalex.org/W3196155444","https://openalex.org/W4321844043","https://openalex.org/W3210156800","https://openalex.org/W4390062853","https://openalex.org/W4297883248","https://openalex.org/W4255830763","https://openalex.org/W1583266947"],"abstract_inverted_index":{"We":[0,100],"present":[1],"VidedWhisfer,":[2],"a":[3,18,45,51,78],"novel":[4,79],"approach":[5],"for":[6,39],"unsupervised":[7],"video":[8,13,29,41,106,117,131],"representation":[9,107,118],"learning,":[10],"in":[11],"which":[12,58],"sequence":[14,27,52,72],"is":[15,75,91,122],"treated":[16],"as":[17,130],"self-supervision":[19],"entity":[20],"based":[21],"on":[22],"the":[23,26,64,71,97,109],"observation":[24],"that":[25,116],"encodes":[28,59],"temporal":[30],"dynamics":[31,69],"(e.g.,":[32],"object":[33],"movement":[34],"and":[35,67,93,133],"event":[36],"evolution).":[37],"Specifically,":[38],"each":[40],"sequence,":[42],"we":[43,114],"use":[44],"pre-learned":[46],"visual":[47,61,68],"dictionary":[48],"to":[49,95,104,124],"generate":[50,105],"of":[53],"high-level":[54],"semantics,":[55],"dubbed":[56],"\u201cwhisper\u201d,":[57],"both":[60],"contents":[62],"at":[63,70],"frame":[65],"level":[66],"level.":[73],"VidedWhisfer":[74,121],"driven":[76],"by":[77,120],"\u201csequence-to-whisper\u201d":[80],"learning":[81,87],"strategy.":[82],"Naturally,":[83],"an":[84],"end-to-end":[85],"sequence-to-sequence":[86],"model":[88],"using":[89],"RNN":[90],"modeled":[92],"trained":[94],"predict":[96],"whisper":[98],"sequence.":[99],"propose":[101],"two":[102],"ways":[103],"from":[108],"model.":[110],"Through":[111],"extensive":[112],"experiments":[113],"demonstrate":[115],"learned":[119],"effective":[123],"boost":[125],"fundamental":[126],"video-related":[127],"applications":[128],"such":[129],"retrieval":[132],"classification.":[134]},"counts_by_year":[{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}