{"id":"https://openalex.org/W2990964949","doi":"https://doi.org/10.1109/tcsvt.2019.2956593","title":"Convolutional Reconstruction-to-Sequence for Video Captioning","display_name":"Convolutional Reconstruction-to-Sequence for Video Captioning","publication_year":2019,"publication_date":"2019-11-28","ids":{"openalex":"https://openalex.org/W2990964949","doi":"https://doi.org/10.1109/tcsvt.2019.2956593","mag":"2990964949"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2019.2956593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2956593","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5066818276","display_name":"Aming Wu","orcid":"https://orcid.org/0000-0001-8426-0392"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aming Wu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-2024-2678","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031819155","display_name":"Yahong Han","orcid":"https://orcid.org/0000-0003-2768-1398"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahong Han","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-2768-1398","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0512-880X","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qinghua Hu","orcid":"https://orcid.org/0000-0001-8690-987X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Hu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-8690-987X","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2139-8807","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1543,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.88772387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"30","issue":"11","first_page":"4299","last_page":"4308"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8481031656265259},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7539910078048706},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7226254940032959},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6646219491958618},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.654106080532074},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.650630533695221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6223333477973938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5388789176940918},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5253543257713318},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5227846503257751},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5062898397445679},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4939456582069397},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4791697561740875},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.43732404708862305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3417195677757263},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22382989525794983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1810406744480133},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12725406885147095},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08525285124778748},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07084625959396362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481031656265259},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7539910078048706},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7226254940032959},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6646219491958618},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.654106080532074},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.650630533695221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6223333477973938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5388789176940918},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5253543257713318},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5227846503257751},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5062898397445679},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4939456582069397},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4791697561740875},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.43732404708862305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3417195677757263},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22382989525794983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1810406744480133},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12725406885147095},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08525285124778748},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07084625959396362},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2019.2956593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2956593","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/144847","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/144847","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1829462488","display_name":"\u8de8\u5a92\u4f53\u667a\u80fd\u95ee\u7b54\u548c\u63a8\u7406\u5173\u952e\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61932009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4407339161","display_name":null,"funder_award_id":"61876130","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G565454518","display_name":null,"funder_award_id":"U1509206,","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1895577753","https://openalex.org/W1924770834","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2025768430","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2318631040","https://openalex.org/W2343553806","https://openalex.org/W2412782625","https://openalex.org/W2423557781","https://openalex.org/W2425121537","https://openalex.org/W2430148947","https://openalex.org/W2532034655","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2558834163","https://openalex.org/W2559542432","https://openalex.org/W2560346187","https://openalex.org/W2563296158","https://openalex.org/W2605045867","https://openalex.org/W2613904329","https://openalex.org/W2621571501","https://openalex.org/W2625940279","https://openalex.org/W2740118378","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2777622844","https://openalex.org/W2778940641","https://openalex.org/W2808203533","https://openalex.org/W2891955747","https://openalex.org/W2949197413","https://openalex.org/W2949789546","https://openalex.org/W2950553082","https://openalex.org/W2951684117","https://openalex.org/W2953318193","https://openalex.org/W2953333557","https://openalex.org/W2962681491","https://openalex.org/W2962694510","https://openalex.org/W2962907269","https://openalex.org/W2962941628","https://openalex.org/W2963084599","https://openalex.org/W2963119563","https://openalex.org/W2963149042","https://openalex.org/W2963150162","https://openalex.org/W2963355447","https://openalex.org/W2963383024","https://openalex.org/W2963576560","https://openalex.org/W2963636093","https://openalex.org/W2963686907","https://openalex.org/W2963705779","https://openalex.org/W2963717374","https://openalex.org/W2963840672","https://openalex.org/W2963843052","https://openalex.org/W2963937185","https://openalex.org/W2964241990","https://openalex.org/W2964265128","https://openalex.org/W3098682680","https://openalex.org/W6640212811","https://openalex.org/W6679436768","https://openalex.org/W6680145277","https://openalex.org/W6684090549","https://openalex.org/W6685670348","https://openalex.org/W6696085341","https://openalex.org/W6717888560","https://openalex.org/W6728881024","https://openalex.org/W6729995908","https://openalex.org/W6732742072","https://openalex.org/W6737778391","https://openalex.org/W6747016466","https://openalex.org/W6754478056","https://openalex.org/W6754546032","https://openalex.org/W6764115457","https://openalex.org/W6765069029","https://openalex.org/W6898505805"],"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/W4289422896"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"towards":[2],"video":[3,74,100],"captioning":[4],"mainly":[5],"follow":[6],"an":[7],"encoder-decoder":[8,97],"(sequence-to-sequence)":[9],"framework":[10,98],"and":[11,64,156],"generate":[12],"captions":[13],"via":[14],"a":[15,94,115,131,136,145,168,178],"recurrent":[16],"neural":[17,49],"network":[18,50],"(RNN).":[19],"However,":[20],"employing":[21],"RNN":[22],"as":[23,122,144],"the":[24,47,81,123,149,182,185,189],"decoder":[25,186],"(generator)":[26],"is":[27],"prone":[28],"to":[29,37,55,108,113,129,166],"diluting":[30],"long-term":[31,39,172,192],"information,":[32],"which":[33,140],"weakens":[34],"its":[35],"ability":[36,63],"capture":[38],"dependencies.":[40],"Recently,":[41],"some":[42],"work":[43],"has":[44,68],"demonstrated":[45],"that":[46,121,200],"convolutional":[48,138,164],"(CNN)":[51],"could":[52,141,174,187,203],"be":[53,130,142,175],"used":[54],"model":[56],"sequential":[57],"information.":[58,193],"Though":[59],"strengths":[60],"in":[61,73],"representation":[62],"computation":[65],"efficiency,":[66],"CNN":[67],"not":[69],"been":[70],"well":[71],"exploited":[72],"captioning.":[75,101],"The":[76],"reason":[77],"partially":[78],"comes":[79],"from":[80],"difficulty":[82],"of":[83,191],"modeling":[84],"multi-modal":[85],"sequence":[86],"with":[87,120],"CNN.":[88],"In":[89,148],"this":[90],"paper,":[91],"we":[92,103,125,152,160],"devise":[93],"novel":[95],"CNN-based":[96],"for":[99],"Particularly,":[102],"first":[104,153],"append":[105],"inter-frame":[106],"differences":[107],"each":[109,127],"CNN-extracted":[110],"frame":[111,128],"feature":[112,134],"get":[114],"more":[116,132],"discriminative":[117],"representation;":[118],"then":[119,159],"input,":[124],"encode":[126],"compact":[133],"by":[135,177],"one-layer":[137],"mapping,":[139],"taken":[143],"reconstruction":[146],"network.":[147],"decoding":[150],"stage,":[151],"fuse":[154],"visual":[155],"lexical":[157],"feature;":[158],"stack":[161],"multiple":[162],"dilated":[163],"layers":[165],"form":[167],"hierarchical":[169,183],"decoder.":[170],"As":[171],"dependencies":[173],"captured":[176],"shorter":[179],"path":[180],"along":[181],"structure,":[184],"alleviate":[188],"loss":[190],"Experiments":[194],"on":[195],"two":[196],"benchmark":[197],"datasets":[198],"show":[199],"our":[201],"method":[202],"obtain":[204],"state-of-the-art":[205],"performance.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}