{"id":"https://openalex.org/W4284692156","doi":"https://doi.org/10.1145/3546828","title":"Learning Video-Text Aligned Representations for Video Captioning","display_name":"Learning Video-Text Aligned Representations for Video Captioning","publication_year":2022,"publication_date":"2022-07-07","ids":{"openalex":"https://openalex.org/W4284692156","doi":"https://doi.org/10.1145/3546828"},"language":"en","primary_location":{"id":"doi:10.1145/3546828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546828","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5019915855","display_name":"Yaya Shi","orcid":"https://orcid.org/0000-0003-0465-6712"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaya Shi","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0465-6712","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544410","display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0001-9442-5912"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9442-5912","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005377211","display_name":"Chunfeng Yuan","orcid":"https://orcid.org/0000-0003-2219-4961"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunfeng Yuan","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2219-4961","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451204","display_name":"Bing Li","orcid":"https://orcid.org/0000-0001-6114-1411"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6114-1411","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114549594","display_name":"Weiming Hu","orcid":"https://orcid.org/0000-0001-9237-8825"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Hu","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, China and School of ArtificialIntelligence, University of Chinese Academy of Sciences, China and CAS Center for Excellence in BrainScience and Intelligence Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9237-8825","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China and School of ArtificialIntelligence, University of Chinese Academy of Sciences, China and CAS Center for Excellence in BrainScience and Intelligence Technology, Beijing, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2510-8993","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9436,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87224591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9972000122070312,"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":0.9948999881744385,"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":0.9729722738265991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8702876567840576},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5667555928230286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5438339114189148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306799411773682},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5056190490722656},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4869168996810913},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3570970892906189},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20701897144317627},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.17089682817459106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10363206267356873}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9729722738265991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8702876567840576},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5667555928230286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5438339114189148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306799411773682},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5056190490722656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4869168996810913},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3570970892906189},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20701897144317627},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.17089682817459106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10363206267356873},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3546828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546828","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4674801117","display_name":null,"funder_award_id":"WK2100000024","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6052960980","display_name":null,"funder_award_id":"2020AAA0105702","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7169530124","display_name":null,"funder_award_id":"61972397, 62036011, 62192782, 61721004, U19B2038, 61906192","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1601567445","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2012210378","https://openalex.org/W2194775991","https://openalex.org/W2525778437","https://openalex.org/W2600463316","https://openalex.org/W2604738282","https://openalex.org/W2613454500","https://openalex.org/W2619947201","https://openalex.org/W2911285743","https://openalex.org/W2938603906","https://openalex.org/W2942992487","https://openalex.org/W2962934715","https://openalex.org/W2963170456","https://openalex.org/W2963355794","https://openalex.org/W2981750519","https://openalex.org/W2996817764","https://openalex.org/W3035372819","https://openalex.org/W3134875898","https://openalex.org/W3135367836","https://openalex.org/W3152798676","https://openalex.org/W3157700644","https://openalex.org/W3166396011","https://openalex.org/W3167051144","https://openalex.org/W3175939205","https://openalex.org/W3176799298","https://openalex.org/W3177525997","https://openalex.org/W3211865849","https://openalex.org/W4205807230","https://openalex.org/W4225909425","https://openalex.org/W4247924304","https://openalex.org/W4249502209","https://openalex.org/W4249914127","https://openalex.org/W4255556797","https://openalex.org/W6758142211","https://openalex.org/W6766003984","https://openalex.org/W6791195152","https://openalex.org/W6811440883","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W3161079477","https://openalex.org/W2750434199","https://openalex.org/W4386924096","https://openalex.org/W2129428289","https://openalex.org/W2347374138","https://openalex.org/W2050635624","https://openalex.org/W2091753323","https://openalex.org/W2101447046","https://openalex.org/W2168037874","https://openalex.org/W2119303512"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"requires":[2],"that":[3,203,217],"the":[4,7,19,35,40,43,46,50,58,64,71,125,141,144,151],"model":[5],"has":[6,60],"abilities":[8],"of":[9,143,156],"video":[10,106,145],"understanding,":[11],"video-text":[12,27,89,102,152,169],"alignment,":[13],"and":[14,24,74,96,131,146,200,222],"text":[15],"generation.":[16],"Due":[17],"to":[18,33,45,61,78,100,115,149,174],"semantic":[20,36,126,165,184],"gap":[21],"between":[22,128],"vision":[23],"language,":[25],"conducting":[26],"alignment":[28,90,98,138],"is":[29,122],"a":[30,88,93,112,163,210],"crucial":[31],"step":[32],"reduce":[34],"gap,":[37],"which":[38,69,121,186],"maps":[39],"representations":[41,66,104,155,171],"from":[42],"visual":[44,65,129],"language":[47,132],"domain.":[48],"However,":[49],"existing":[51],"methods":[52],"often":[53],"overlook":[54],"this":[55,84],"step,":[56],"so":[57],"decoder":[59],"directly":[62],"take":[63],"as":[67,118,124],"input,":[68],"increases":[70],"decoder\u2019s":[72],"workload":[73],"limits":[75],"its":[76],"ability":[77],"generate":[79,175],"semantically":[80,176],"correct":[81,177,221],"captions.":[82,178,192,224],"In":[83],"paper,":[85],"we":[86,109,135],"propose":[87,111],"module":[91],"with":[92,140],"retrieval":[94,113],"unit":[95,99,114,139],"an":[97,137],"learn":[101],"aligned":[103,161,170],"for":[105,189],"captioning.":[107],"Specifically,":[108],"firstly":[110],"retrieve":[116],"sentences":[117,148,181],"additional":[119],"input":[120,142],"used":[123,173],"anchor":[127],"scene":[130],"description.":[133],"Then,":[134],"employ":[136],"retrieved":[147,180],"conduct":[150],"alignment.":[153],"The":[154,167,213],"two":[157,195],"modal":[158],"inputs":[159],"are":[160,172,187],"in":[162],"shared":[164],"space.":[166],"obtained":[168],"Moreover,":[179],"provide":[182],"rich":[183],"concepts":[185],"helpful":[188],"generating":[190],"distinctive":[191,223],"Experiments":[193],"on":[194],"public":[196],"benchmarks,":[197],"i.e.,":[198],"VATEX":[199],"MSR-VTT,":[201],"demonstrate":[202],"our":[204,218],"method":[205,219],"outperforms":[206],"state-of-the-art":[207],"performances":[208],"by":[209],"large":[211],"margin.":[212],"qualitative":[214],"analysis":[215],"shows":[216],"generates":[220]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}