{"id":"https://openalex.org/W3132101720","doi":"https://doi.org/10.3390/fi13020055","title":"Video Captioning Based on Channel Soft Attention and Semantic Reconstructor","display_name":"Video Captioning Based on Channel Soft Attention and Semantic Reconstructor","publication_year":2021,"publication_date":"2021-02-23","ids":{"openalex":"https://openalex.org/W3132101720","doi":"https://doi.org/10.3390/fi13020055","mag":"3132101720"},"language":"en","primary_location":{"id":"doi:10.3390/fi13020055","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi13020055","pdf_url":"https://www.mdpi.com/1999-5903/13/2/55/pdf?version=1614230426","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/13/2/55/pdf?version=1614230426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058737960","display_name":"Lei Zhou","orcid":"https://orcid.org/0000-0003-0860-0724"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Lei","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088202431","display_name":"Yiyong Huang","orcid":"https://orcid.org/0000-0002-5977-4786"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiyong Huang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088202431"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.5537,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84726644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"13","issue":"2","first_page":"55","last_page":"55"},"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9275100231170654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.914120078086853},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7093707919120789},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6596661806106567},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6071348786354065},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5677594542503357},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5165058970451355},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.49760153889656067},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45232874155044556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43656036257743835},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4247230291366577},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40458717942237854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38840439915657043},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15314936637878418},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11983075737953186},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11450237035751343},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11169323325157166}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9275100231170654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.914120078086853},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7093707919120789},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6596661806106567},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6071348786354065},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5677594542503357},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5165058970451355},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.49760153889656067},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45232874155044556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43656036257743835},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4247230291366577},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40458717942237854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38840439915657043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15314936637878418},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11983075737953186},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11450237035751343},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11169323325157166},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/fi13020055","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi13020055","pdf_url":"https://www.mdpi.com/1999-5903/13/2/55/pdf?version=1614230426","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:13:y:2021:i:2:p:55-:d:504533","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/13/2/55/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:89bfa7894d3943d8ac3192fd02d5c046","is_oa":true,"landing_page_url":"https://doaj.org/article/89bfa7894d3943d8ac3192fd02d5c046","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 13, Iss 2, p 55 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-5903/13/2/55/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/fi13020055","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet; Volume 13; Issue 2; Pages: 55","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/fi13020055","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi13020055","pdf_url":"https://www.mdpi.com/1999-5903/13/2/55/pdf?version=1614230426","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G5843839860","display_name":null,"funder_award_id":"No. 19511121002","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7658930221","display_name":null,"funder_award_id":"No. 61572306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8437091502","display_name":null,"funder_award_id":"NO. 2017YFB0701600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132101720.pdf","grobid_xml":"https://content.openalex.org/works/W3132101720.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1956340063","https://openalex.org/W1966385142","https://openalex.org/W2012592962","https://openalex.org/W2016053056","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2105101328","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2126574503","https://openalex.org/W2132034999","https://openalex.org/W2133512280","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2164290393","https://openalex.org/W2172010943","https://openalex.org/W2250539671","https://openalex.org/W2302086703","https://openalex.org/W2308045930","https://openalex.org/W2425121537","https://openalex.org/W2507365558","https://openalex.org/W2508429489","https://openalex.org/W2523937091","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2737030113","https://openalex.org/W2795215224","https://openalex.org/W2808203533","https://openalex.org/W2904022486","https://openalex.org/W2946185384","https://openalex.org/W2949447259","https://openalex.org/W2950133940","https://openalex.org/W2951390634","https://openalex.org/W2951559372","https://openalex.org/W2953022181","https://openalex.org/W2953022248","https://openalex.org/W2962681491","https://openalex.org/W2963420686","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2964018924","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W3035284526","https://openalex.org/W4239999461","https://openalex.org/W4241881238","https://openalex.org/W4294170691","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638549007","https://openalex.org/W6682631176","https://openalex.org/W6682691769","https://openalex.org/W6684090549","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4386858688","https://openalex.org/W2982536526","https://openalex.org/W4380302312","https://openalex.org/W3008689640","https://openalex.org/W4385338604","https://openalex.org/W3081626085"],"abstract_inverted_index":{"Video":[0],"captioning":[1,18,100],"is":[2,110,133,173],"a":[3,9,98,121,170],"popular":[4,208],"task":[5],"which":[6,87,112,190],"automatically":[7],"generates":[8],"natural-language":[10],"sentence":[11],"to":[12,33,159,165,175,179,197,202],"describe":[13],"video":[14,17,99,122,167],"content.":[15],"Previous":[16],"works":[19],"mainly":[20],"use":[21],"the":[22,35,74,114,126,136,143,153,181,187,214],"encoder\u2013decoder":[23],"framework":[24],"and":[25,49,107,150,199,211,216],"exploit":[26],"special":[27],"techniques":[28],"such":[29],"as":[30,67],"attention":[31,43,106],"mechanisms":[32,44],"improve":[34],"quality":[36],"of":[37,77,92,129,156,183,193,218],"generated":[38,134,145],"sentences.":[39],"In":[40,95,120],"addition,":[41],"most":[42],"focus":[45],"on":[46,103,207],"global":[47,53,115],"features":[48,54,66,144],"spatial":[50],"features.":[51,59],"However,":[52],"are":[55],"usually":[56],"fully":[57],"connected":[58],"Recurrent":[60],"convolution":[61],"networks":[62],"(RCNs)":[63],"receive":[64],"3-dimensional":[65],"input":[68,152],"at":[69,80,161],"each":[70,78,81,93,118,147,157,162],"time":[71,82,131,163],"step,":[72],"but":[73],"temporal":[75,89],"structure":[76],"channel":[79,104,128,158],"step":[83,132,164],"has":[84],"been":[85],"ignored,":[86],"provide":[88],"relation":[90],"information":[91,116,185],"channel.":[94,119],"this":[96],"paper,":[97],"model":[101],"based":[102],"soft":[105],"semantic":[108,171,177,184],"reconstructor":[109,172],"proposed,":[111],"considers":[113],"for":[117],"feature":[123],"map":[124],"sequence,":[125],"same":[127,137],"every":[130],"by":[135,146],"convolutional":[138,148],"kernel.":[139],"We":[140],"selectively":[141],"collect":[142],"kernel":[149],"then":[151],"weighted":[154],"sum":[155],"RCN":[160],"encode":[166],"representation.":[168],"Furthermore,":[169],"proposed":[174],"rebuild":[176],"vectors":[178],"ensure":[180],"integrity":[182],"in":[186],"training":[188],"process,":[189],"takes":[191],"advantage":[192],"both":[194],"forward":[195],"(semantic":[196],"sentence)":[198],"backward":[200],"(sentence":[201],"semantic)":[203],"flows.":[204],"Experimental":[205],"results":[206],"datasets":[209],"MSVD":[210],"MSR-VTT":[212],"demonstrate":[213],"effectiveness":[215],"feasibility":[217],"our":[219],"model.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2021-03-01T00:00:00"}