{"id":"https://openalex.org/W3001795741","doi":"https://doi.org/10.1109/icce-berlin47944.2019.8966173","title":"Video Captioning Based on Joint Image\u2013Audio Deep Learning Techniques","display_name":"Video Captioning Based on Joint Image\u2013Audio Deep Learning Techniques","publication_year":2019,"publication_date":"2019-09-08","ids":{"openalex":"https://openalex.org/W3001795741","doi":"https://doi.org/10.1109/icce-berlin47944.2019.8966173","mag":"3001795741"},"language":"en","primary_location":{"id":"doi:10.1109/icce-berlin47944.2019.8966173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-berlin47944.2019.8966173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 9th International Conference on Consumer Electronics (ICCE-Berlin)","raw_type":"proceedings-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/A5072470661","display_name":"Chien-Yao Wang","orcid":"https://orcid.org/0000-0002-2946-8972"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chien-Yao Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091405861","display_name":"Pei-Sin Liaw","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pei-Sin Liaw","raw_affiliation_strings":["Department of Communication Engineering, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Communication Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451175","display_name":"Kai-Wen Liang","orcid":"https://orcid.org/0000-0002-7130-1957"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Wen Liang","raw_affiliation_strings":["Department of Communication Engineering, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Communication Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059622590","display_name":"Jai-Ching Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jai-Ching Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103030114","display_name":"Pao\u2010Chi Chang","orcid":"https://orcid.org/0000-0003-3097-4714"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pao-Chi Chang","raw_affiliation_strings":["Department of Communication Engineering, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Communication Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072470661"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.3317,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58671904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9959999918937683,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9943000078201294,"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":0.8908771276473999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8804316520690918},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6512452363967896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6165056824684143},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.599946916103363},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5942882299423218},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5702885389328003},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5354699492454529},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5053680539131165},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45374661684036255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4016610085964203}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8908771276473999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804316520690918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6512452363967896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6165056824684143},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.599946916103363},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5942882299423218},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5702885389328003},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5354699492454529},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5053680539131165},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45374661684036255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4016610085964203},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1109/icce-berlin47944.2019.8966173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-berlin47944.2019.8966173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 9th International Conference on Consumer Electronics (ICCE-Berlin)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1907729166","https://openalex.org/W1956340063","https://openalex.org/W2016053056","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2558834163","https://openalex.org/W2566935005","https://openalex.org/W2766375149","https://openalex.org/W2785892019","https://openalex.org/W2786670585","https://openalex.org/W2799759589","https://openalex.org/W2895845501","https://openalex.org/W2964121744","https://openalex.org/W2964241990","https://openalex.org/W3103850820","https://openalex.org/W6678262379","https://openalex.org/W6680145277","https://openalex.org/W6682631176","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2785892019","https://openalex.org/W3042165234","https://openalex.org/W3212315886","https://openalex.org/W3204936728","https://openalex.org/W3033014863","https://openalex.org/W3210290507","https://openalex.org/W3021938736","https://openalex.org/W3162251280","https://openalex.org/W3122335742","https://openalex.org/W2901467237","https://openalex.org/W3202567960","https://openalex.org/W2945961616","https://openalex.org/W3090602574","https://openalex.org/W3036736353","https://openalex.org/W2790776232","https://openalex.org/W3034815696","https://openalex.org/W2911868273","https://openalex.org/W3131003920","https://openalex.org/W3047151004","https://openalex.org/W2731627339"],"abstract_inverted_index":{"With":[0],"the":[1,61,91,94,103,113,120],"advancement":[2],"in":[3],"technology,":[4],"deep":[5],"learning":[6],"has":[7],"been":[8],"widely":[9],"used":[10,85],"for":[11,54],"various":[12],"multimedia":[13],"applications.":[14],"Herein,":[15],"we":[16],"utilized":[17],"this":[18],"technology":[19],"to":[20,30,64,86,99],"video":[21],"captioning.":[22],"The":[23,56,131],"proposed":[24],"system":[25],"uses":[26],"different":[27],"neural":[28],"networks":[29],"extract":[31],"features":[32,42,59],"from":[33],"image,":[34],"audio,":[35],"and":[36,40,119,122,128],"semantic":[37],"signals.":[38],"Image":[39],"audio":[41],"are":[43],"concatenated":[44],"before":[45],"being":[46],"fed":[47],"into":[48],"a":[49,66],"long":[50],"short-term":[51],"memory":[52],"(LSTM)":[53],"initialization.":[55],"joint":[57],"audio-image":[58],"help":[60],"entire":[62],"semantics":[63],"form":[65],"network":[67],"with":[68,102],"better":[69],"performance.":[70],"A":[71],"bilingual":[72],"evaluation":[73],"understudy":[74],"algorithm":[75],"(BLEU)":[76],"-":[77,83],"an":[78],"automatic":[79],"speech":[80],"scoring":[81],"mechanism":[82],"was":[84],"score":[87,115],"sentences.":[88],"We":[89],"considered":[90],"length":[92],"of":[93,105],"word":[95,98],"group":[96],"(one":[97],"four":[100],"words);":[101],"increase":[104],"all":[106],"BLEU":[107],"scores":[108,124],"by":[109,117,126],"more":[110],"than":[111],"1%,":[112],"CIDEr-D":[114],"increased":[116,125],"2.27%,":[118],"METEOR":[121],"ROUGE-L":[123],"0.2%":[127],"0.7%,":[129],"respectively.":[130],"improvement":[132],"is":[133],"highly":[134],"significant.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}