{"id":"https://openalex.org/W3093026747","doi":"https://doi.org/10.1145/3394171.3413908","title":"Controllable Video Captioning with an Exemplar Sentence","display_name":"Controllable Video Captioning with an Exemplar Sentence","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093026747","doi":"https://doi.org/10.1145/3394171.3413908","mag":"3093026747"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.01073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011133696","display_name":"Yitian Yuan","orcid":"https://orcid.org/0000-0001-8701-7689"},"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":"Yitian Yuan","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan-Dianping Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan-Dianping Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461874","display_name":"Jingwen Wang","orcid":"https://orcid.org/0000-0002-1405-4697"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"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":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011133696"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.3739,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.83999269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1085","last_page":"1093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11439","display_name":"Video Analysis and Summarization","score":0.9969000220298767,"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":0.9968000054359436,"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/closed-captioning","display_name":"Closed captioning","score":0.9587585926055908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8804166316986084},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7695214748382568},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.6953107714653015},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6631220579147339},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6174975633621216},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6096904873847961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5678479075431824},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4125102758407593},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38883060216903687},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1340177059173584},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11540564894676208}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9587585926055908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804166316986084},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7695214748382568},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6953107714653015},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6631220579147339},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6174975633621216},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6096904873847961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5678479075431824},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4125102758407593},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38883060216903687},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1340177059173584},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11540564894676208},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3413908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2112.01073","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.01073","pdf_url":"https://arxiv.org/pdf/2112.01073","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.01073","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.01073","pdf_url":"https://arxiv.org/pdf/2112.01073","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1522301498","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W1601567445","https://openalex.org/W1976373002","https://openalex.org/W2064675550","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2123442489","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2250539671","https://openalex.org/W2274287116","https://openalex.org/W2425121537","https://openalex.org/W2525364784","https://openalex.org/W2545656684","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2603266952","https://openalex.org/W2625940279","https://openalex.org/W2727849499","https://openalex.org/W2766375149","https://openalex.org/W2786399470","https://openalex.org/W2798569372","https://openalex.org/W2799009156","https://openalex.org/W2892245540","https://openalex.org/W2923793772","https://openalex.org/W2950579554","https://openalex.org/W2953119472","https://openalex.org/W2954841306","https://openalex.org/W2962681491","https://openalex.org/W2962799512","https://openalex.org/W2962937869","https://openalex.org/W2963084773","https://openalex.org/W2963177403","https://openalex.org/W2963267809","https://openalex.org/W2963304263","https://openalex.org/W2963576560","https://openalex.org/W2963743213","https://openalex.org/W2963916161","https://openalex.org/W2963971014","https://openalex.org/W2964065937","https://openalex.org/W2964121744","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W2970898753","https://openalex.org/W2982553922","https://openalex.org/W2984862483","https://openalex.org/W3098682680","https://openalex.org/W4210896998","https://openalex.org/W4299341000","https://openalex.org/W4302375066"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W3217195652"],"abstract_inverted_index":{"In":[0,56],"this":[1],"paper,":[2],"we":[3,66],"investigate":[4],"a":[5,20,23,68,183],"novel":[6,69],"and":[7,22,90,95,125,159],"challenging":[8],"task,":[9,65],"namely":[10],"controllable":[11,158],"video":[12,21,63,84,143,162,191],"captioning":[13,64,144],"with":[14,102,177],"an":[15,61,77,88],"exemplar":[16,26,54,112,138,167],"sentence.":[17,55,113],"Formally,":[18],"given":[19,53,111],"syntactically":[24],"valid":[25],"sentence,":[27],"the":[28,39,43,48,52,93,105,110,120,127,150,188],"task":[29],"aims":[30],"to":[31,58,104,118,186],"generate":[32],"one":[33],"caption":[34,130],"which":[35],"not":[36],"only":[37],"describes":[38],"semantic":[40,85,160],"contents":[41],"of":[42,51,97,109,152,173,190],"video,":[44],"but":[45],"also":[46],"follows":[47],"syntactic":[49,107,179],"form":[50],"order":[57],"tackle":[59],"such":[60],"exemplar-based":[62],"propose":[67],"Syntax":[70],"Modulated":[71],"Caption":[72],"Generator":[73],"(SMCG)":[74],"incorporated":[75],"in":[76],"encoder-decoder-reconstructor":[78],"architecture.":[79],"The":[80],"proposed":[81],"SMCG":[82,115],"takes":[83],"representation":[86],"as":[87],"input,":[89],"conditionally":[91],"modulates":[92],"gates":[94],"cells":[96],"long":[98],"short-term":[99],"memory":[100],"network":[101],"respect":[103],"encoded":[106],"information":[108],"Therefore,":[114],"is":[116,171],"able":[117],"control":[119],"states":[121],"for":[122,140],"word":[123],"prediction":[124],"achieve":[126],"syntax":[128,157],"customized":[129],"generation.":[131],"We":[132],"conduct":[133],"experiments":[134],"by":[135],"collecting":[136],"auxiliary":[137],"sentences":[139],"two":[141],"public":[142],"datasets.":[145],"Extensive":[146],"experimental":[147],"results":[148],"demonstrate":[149],"effectiveness":[151],"our":[153,169],"approach":[154,170],"on":[155],"generating":[156],"preserved":[161],"captions.":[163],"By":[164],"providing":[165],"different":[166,175],"sentences,":[168],"capable":[172],"producing":[174],"captions":[176],"various":[178],"structures,":[180],"thus":[181],"indicating":[182],"promising":[184],"way":[185],"strengthen":[187],"diversity":[189],"captioning.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}