{"id":"https://openalex.org/W3216620107","doi":"https://doi.org/10.1109/tpami.2021.3131618","title":"Syntax Customized Video Captioning by Imitating Exemplar Sentences","display_name":"Syntax Customized Video Captioning by Imitating Exemplar Sentences","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W3216620107","doi":"https://doi.org/10.1109/tpami.2021.3131618","mag":"3216620107","pmid":"https://pubmed.ncbi.nlm.nih.gov/34847021"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3131618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3131618","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yitian Yuan","orcid":"https://orcid.org/0000-0001-8701-7689"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yitian Yuan","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":null,"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":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210087373"],"apc_list":null,"apc_paid":null,"fwci":0.3884,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.62428502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"44","issue":"12","first_page":"10209","last_page":"10221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9718000292778015,"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":0.9718000292778015,"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":0.005400000140070915,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9437000155448914},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.76910001039505},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5738999843597412},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41769999265670776},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3869999945163727},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3741999864578247}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9437000155448914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8671000003814697},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.76910001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478000283241272},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5724999904632568},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25049999356269836}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014743","descriptor_name":"Videotape Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014743","descriptor_name":"Videotape Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014743","descriptor_name":"Videotape Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3131618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3131618","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34847021","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34847021","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5866751179","display_name":null,"funder_award_id":"62050110","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W1931639407","https://openalex.org/W1976373002","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2123442489","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2250539671","https://openalex.org/W2250562110","https://openalex.org/W2425121537","https://openalex.org/W2557264465","https://openalex.org/W2625940279","https://openalex.org/W2766375149","https://openalex.org/W2798851324","https://openalex.org/W2954841306","https://openalex.org/W2962681491","https://openalex.org/W2962937869","https://openalex.org/W2962968835","https://openalex.org/W2963267809","https://openalex.org/W2963743213","https://openalex.org/W2963916161","https://openalex.org/W2964008635","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W2964532449","https://openalex.org/W2982553922","https://openalex.org/W2984862483","https://openalex.org/W3034984754","https://openalex.org/W3083526914","https://openalex.org/W3099066892","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6748197246","https://openalex.org/W6754478056","https://openalex.org/W6766978945","https://openalex.org/W6768817161","https://openalex.org/W6769888028","https://openalex.org/W6788051698"],"related_works":[],"abstract_inverted_index":{"Enhancing":[0],"the":[1,69,76,82,103,107,120,150,163],"diversity":[2,175],"of":[3,30,53,106,170],"sentences":[4,160,194],"to":[5,60,101,118,161,182],"describe":[6],"video":[7,16,32,42,70,89,125,135,153,187],"contents":[8,71],"is":[9,98,116,129,199],"an":[10],"important":[11],"problem":[12,25],"arising":[13],"in":[14,168],"recent":[15],"captioning":[17,90,154],"research.":[18],"In":[19],"this":[20,24],"paper,":[21],"we":[22,48,85,137],"explore":[23],"from":[26],"a":[27,41,50,87,93,111,140,144],"novel":[28,88],"perspective":[29],"customizing":[31],"captions":[33,188],"by":[34,142],"imitating":[35],"exemplar":[36,46,78,108,159,193],"sentence":[37,95],"syntaxes.":[38],"Specifically,":[39],"given":[40,77],"and":[43,156,174,185],"any":[44],"syntax-valid":[45],"sentence,":[47,109],"introduce":[49],"new":[51,145],"task":[52],"Syntax":[54],"Customized":[55],"Video":[56],"Captioning":[57],"(SCVC)":[58],"aiming":[59],"generate":[61,119,183],"one":[62],"caption":[63,114,123],"which":[64,148],"not":[65],"only":[66],"semantically":[67],"describes":[68],"but":[72],"also":[73],"syntactically":[74,121],"imitates":[75],"sentence.":[79],"To":[80],"tackle":[81,138],"SCVC":[83],"task,":[84],"propose":[86],"model,":[91],"where":[92],"hierarchical":[94],"syntax":[96,112,132],"encoder":[97],"first":[99],"designed":[100],"extract":[102],"syntactic":[104],"structure":[105],"then":[110],"conditioned":[113],"decoder":[115],"devised":[117],"structured":[122],"expressing":[124],"semantics.":[126],"As":[127],"there":[128],"no":[130],"available":[131,200],"customized":[133],"groundtruth":[134],"captions,":[136],"such":[139],"challenge":[141],"proposing":[143],"training":[146],"strategy,":[147],"leverages":[149],"traditional":[151],"pairwise":[152],"data":[155],"our":[157,179],"collected":[158],"accomplish":[162],"model":[164,180],"learning.":[165],"Extensive":[166],"experiments,":[167],"terms":[169],"semantic,":[171],"syntactic,":[172],"fluency,":[173],"evaluations,":[176],"clearly":[177],"demonstrate":[178],"capability":[181],"syntax-varied":[184],"semantics-coherent":[186],"that":[189],"well":[190],"imitate":[191],"different":[192],"with":[195],"enriched":[196],"diversities.":[197],"Code":[198],"at":[201],"https://github.com/yytzsy/Syntax-Customized-Video-Captioning.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2021-12-06T00:00:00"}