{"id":"https://openalex.org/W2962958773","doi":"https://doi.org/10.1109/tnnls.2018.2851077","title":"From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning","display_name":"From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning","publication_year":2018,"publication_date":"2018-08-16","ids":{"openalex":"https://openalex.org/W2962958773","doi":"https://doi.org/10.1109/tnnls.2018.2851077","mag":"2962958773","pmid":"https://pubmed.ncbi.nlm.nih.gov/30130235"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2851077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2851077","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:953b6795-560d-470e-809e-0dda843ecc68","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103213404","display_name":"Yuyu Guo","orcid":"https://orcid.org/0000-0003-4376-6922"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyu Guo","raw_affiliation_strings":["Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Xi\u2019an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi\u2019an, China","Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-2924-946X","affiliations":[{"raw_affiliation_string":"Xi\u2019an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi\u2019an, China","institution_ids":["https://openalex.org/I4210144662"]},{"raw_affiliation_string":"Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, China","institution_ids":["https://openalex.org/I4210144662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037486611","display_name":"Alan Hanjali\u0107","orcid":"https://orcid.org/0000-0002-5771-2549"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alan Hanjalic","raw_affiliation_strings":["Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center of Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.5372,"has_fulltext":true,"cited_by_count":259,"citation_normalized_percentile":{"value":0.99643042,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"30","issue":"10","first_page":"3047","last_page":"3058"},"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":0.9994999766349792,"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":0.9993000030517578,"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/closed-captioning","display_name":"Closed captioning","score":0.9614151120185852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8461247086524963},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.731584906578064},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.661055862903595},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5277755260467529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5125026702880859},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49577125906944275},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4484918415546417},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37762945890426636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3211168646812439},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21930161118507385},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18118354678153992}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9614151120185852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461247086524963},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.731584906578064},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.661055862903595},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5277755260467529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5125026702880859},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49577125906944275},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4484918415546417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37762945890426636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3211168646812439},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21930161118507385},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18118354678153992},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tnnls.2018.2851077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2851077","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:30130235","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30130235","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 neural networks and learning systems","raw_type":null},{"id":"pmh:tud:oai:tudelft.nl:uuid:953b6795-560d-470e-809e-0dda843ecc68","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:953b6795-560d-470e-809e-0dda843ecc68","pdf_url":"http://resolver.tudelft.nl/uuid:953b6795-560d-470e-809e-0dda843ecc68","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:ir.opt.ac.cn:181661/31880","is_oa":true,"landing_page_url":"http://ir.opt.ac.cn/handle/181661/31880","pdf_url":null,"source":{"id":"https://openalex.org/S4377196962","display_name":"Institutional Repository of Xi'an Institute of Optics and Fine Mechanics, Chinese Academy of Sciences (Xian Institute of Optics and Precision Mechanics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144662","host_organization_name":"Xi'an Institute of Optics and Precision Mechanics","host_organization_lineage":["https://openalex.org/I4210144662"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"\u671f\u520a\u8bba\u6587"}],"best_oa_location":{"id":"pmh:tud:oai:tudelft.nl:uuid:953b6795-560d-470e-809e-0dda843ecc68","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:953b6795-560d-470e-809e-0dda843ecc68","pdf_url":"http://resolver.tudelft.nl/uuid:953b6795-560d-470e-809e-0dda843ecc68","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G1150524711","display_name":null,"funder_award_id":"ZYGX2014Z007","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1474490597","display_name":null,"funder_award_id":"111 Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3623292902","display_name":null,"funder_award_id":"61632007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6598207522","display_name":null,"funder_award_id":"ZYGX2014J063","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7095600686","display_name":null,"funder_award_id":"61602049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7413685474","display_name":null,"funder_award_id":"61502080","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7524108349","display_name":null,"funder_award_id":"61761130079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8023235389","display_name":null,"funder_award_id":"2018YFB1107400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8027008232","display_name":"\u534f\u540c\u6df1\u5ea6\u89c6\u9891\u7406\u89e3\u3001\u63cf\u8ff0\u548c\u89c6\u89c9\u95ee\u7b54\u7684\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8199110050","display_name":null,"funder_award_id":"2018YFB1107400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8622808977","display_name":null,"funder_award_id":"B17008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8978917354","display_name":null,"funder_award_id":"B17008","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962958773.pdf","grobid_xml":"https://content.openalex.org/works/W2962958773.grobid-xml"},"referenced_works_count":95,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W20974380","https://openalex.org/W179875071","https://openalex.org/W592244745","https://openalex.org/W639708223","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1686810756","https://openalex.org/W1889081078","https://openalex.org/W1897761818","https://openalex.org/W1924770834","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1959608418","https://openalex.org/W2010632104","https://openalex.org/W2035434106","https://openalex.org/W2064675550","https://openalex.org/W2075966418","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2110485445","https://openalex.org/W2110933980","https://openalex.org/W2121772968","https://openalex.org/W2122180654","https://openalex.org/W2125707784","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2141130481","https://openalex.org/W2152175008","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2176035349","https://openalex.org/W2188365844","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2331050942","https://openalex.org/W2341680599","https://openalex.org/W2396566817","https://openalex.org/W2411707397","https://openalex.org/W2425121537","https://openalex.org/W2513281263","https://openalex.org/W2526868004","https://openalex.org/W2527145521","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2578466053","https://openalex.org/W2598003564","https://openalex.org/W2600383743","https://openalex.org/W2605055943","https://openalex.org/W2613718673","https://openalex.org/W2621571501","https://openalex.org/W2739107216","https://openalex.org/W2751125921","https://openalex.org/W2751445731","https://openalex.org/W2752930373","https://openalex.org/W2764242203","https://openalex.org/W2765860780","https://openalex.org/W2780838211","https://openalex.org/W2781821509","https://openalex.org/W2786585376","https://openalex.org/W2949828251","https://openalex.org/W2962835968","https://openalex.org/W2963279312","https://openalex.org/W2963576560","https://openalex.org/W2963790827","https://openalex.org/W2963843052","https://openalex.org/W2964241990","https://openalex.org/W3022187094","https://openalex.org/W3099677434","https://openalex.org/W4254816979","https://openalex.org/W6600284362","https://openalex.org/W6600861373","https://openalex.org/W6617744952","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6639432524","https://openalex.org/W6640212811","https://openalex.org/W6640963894","https://openalex.org/W6677969093","https://openalex.org/W6680518054","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6685152286","https://openalex.org/W6687045409","https://openalex.org/W6712395597","https://openalex.org/W6712878229","https://openalex.org/W6729624334","https://openalex.org/W6730278946","https://openalex.org/W6730380741","https://openalex.org/W6732875994","https://openalex.org/W6735443497","https://openalex.org/W6736244717","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Video":[0],"captioning,":[1],"in":[2,33,96],"essential,":[3],"is":[4,10,131,152],"a":[5,47,79,118,125,144,148],"complex":[6,64],"natural":[7],"process,":[8],"which":[9,91],"affected":[11],"by":[12,70,158],"various":[13],"uncertainties":[14],"stemming":[15],"from":[16],"video":[17,38,110,119,170,185],"content,":[18],"subjective":[19],"judgment,":[20],"and":[21,40,112,139,172],"so":[22],"on.":[23],"In":[24,74],"this":[25,75],"paper,":[26,76],"we":[27,43,77],"build":[28],"on":[29,164],"the":[30,51,57,71,93,97,107,165,183],"recent":[31],"progress":[32],"using":[34,99],"encoder-decoder":[35],"framework":[36],"for":[37],"captioning":[39,111,186],"address":[41],"what":[42],"find":[44],"to":[45,83,116,134,142,154],"be":[46,67],"critical":[48],"deficiency":[49],"of":[50,56,109],"existing":[52],"methods":[53],"that":[54,177],"most":[55],"decoders":[58],"propagate":[59],"deterministic":[60,72],"hidden":[61],"states.":[62],"Such":[63],"uncertainty":[65,94,156],"cannot":[66],"modeled":[68],"efficiently":[69],"models.":[73],"propose":[78],"generative":[80],"approach,":[81],"referred":[82],"as":[84],"multimodal":[85,126],"stochastic":[86,101,150],"recurrent":[87],"neural":[88],"networks":[89],"(MS-RNNs),":[90],"models":[92],"observed":[95],"data":[98,167],"latent":[100,160],"variables.":[102,161],"Therefore,":[103],"MS-RNN":[104,180],"can":[105],"improve":[106],"performance":[108],"generate":[113],"multiple":[114],"sentences":[115],"describe":[117],"considering":[120],"different":[121],"random":[122],"factors.":[123],"Specifically,":[124],"long":[127],"short-term":[128],"memory":[129],"(LSTM)":[130],"first":[132],"proposed":[133,153,179],"interact":[135],"with":[136],"both":[137],"visual":[138],"textual":[140],"features":[141],"capture":[143],"high-level":[145],"representation.":[146],"Then,":[147],"backward":[149],"LSTM":[151],"support":[155],"propagation":[157],"introducing":[159],"Experimental":[162],"results":[163],"challenging":[166],"sets,":[168],"microsoft":[169,173],"description":[171],"research":[174],"video-to-text,":[175],"show":[176],"our":[178],"approach":[181],"outperforms":[182],"state-of-the-art":[184],"benchmarks.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":76},{"year":2019,"cited_by_count":51},{"year":2018,"cited_by_count":12},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}