{"id":"https://openalex.org/W3210290507","doi":"https://doi.org/10.1109/icccnt51525.2021.9579565","title":"Comparitive study of GRU and LSTM cells based Video Captioning Models","display_name":"Comparitive study of GRU and LSTM cells based Video Captioning Models","publication_year":2021,"publication_date":"2021-07-06","ids":{"openalex":"https://openalex.org/W3210290507","doi":"https://doi.org/10.1109/icccnt51525.2021.9579565","mag":"3210290507"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt51525.2021.9579565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt51525.2021.9579565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5048112638","display_name":"Harsh Maru","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Harsh Maru","raw_affiliation_strings":["Dept of Information Technology, NITK,Karnataka,India"],"affiliations":[{"raw_affiliation_string":"Dept of Information Technology, NITK,Karnataka,India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034343268","display_name":"T. L. Chandana","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tss Chandana","raw_affiliation_strings":["Dept of Information Technology, NITK,Karnataka,India"],"affiliations":[{"raw_affiliation_string":"Dept of Information Technology, NITK,Karnataka,India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037889655","display_name":"Dinesh Naik","orcid":"https://orcid.org/0000-0002-8989-6282"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dinesh Naik","raw_affiliation_strings":["Dept of Information Technology, NITK,Karnataka,India"],"affiliations":[{"raw_affiliation_string":"Dept of Information Technology, NITK,Karnataka,India","institution_ids":["https://openalex.org/I11880225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048112638"],"corresponding_institution_ids":["https://openalex.org/I11880225"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61666667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9881207346916199},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8695933818817139},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6968585848808289},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6607397794723511},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5849633812904358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5638665556907654},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5493414998054504},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.510424792766571},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4890654981136322},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42950439453125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21728381514549255},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2135089635848999}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9881207346916199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8695933818817139},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6968585848808289},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6607397794723511},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5849633812904358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638665556907654},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5493414998054504},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.510424792766571},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4890654981136322},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42950439453125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21728381514549255},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2135089635848999},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt51525.2021.9579565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt51525.2021.9579565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1923404803","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2142900973","https://openalex.org/W2150510224","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2164290393","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2953111739","https://openalex.org/W3093735614","https://openalex.org/W3162814383","https://openalex.org/W3163431160","https://openalex.org/W3163508048","https://openalex.org/W6640257725","https://openalex.org/W6640617836","https://openalex.org/W6678262379","https://openalex.org/W6682144437","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3217195652","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Video":[0,128],"Captioning":[1],"task":[2],"involves":[3,17],"generating":[4],"descriptive":[5],"text":[6],"for":[7,74],"the":[8,13,32,45,55,76,102,123,151],"events":[9],"and":[10,34,97,100,104,118,147],"objects":[11],"in":[12,54],"videos.":[14],"It":[15],"mainly":[16],"taking":[18],"a":[19,25,36,87,134],"video,":[20],"which":[21],"is":[22,64],"nothing":[23],"but":[24],"sequence":[26],"of":[27,42,49,57,61,137],"frames,":[28],"as":[29],"data":[30],"from":[31],"user":[33],"giving":[35],"single":[37],"or":[38,112],"multiple":[39],"sentences":[40],"(sequence":[41],"words)":[43],"to":[44,85,149],"user.":[46],"A":[47],"lot":[48],"research":[50],"has":[51],"been":[52],"done":[53],"area":[56],"video":[58,88],"captioning.":[59],"Most":[60],"this":[62,81],"work":[63],"based":[65],"on":[66,122],"using":[67,91],"Long":[68],"Short":[69],"Term":[70],"Memory":[71],"(LSTM)":[72],"units":[73],"avoiding":[75],"vanishing":[77],"gradients":[78],"problem.":[79],"In":[80],"work,":[82],"we":[83],"purpose":[84],"implement":[86],"captioning":[89],"model":[90,121],"Gated":[92],"Recurrent":[93,113],"Units(GRU's),":[94],"attention":[95],"mechanism":[96],"word":[98],"embeddings":[99],"compare":[101],"functionalities":[103],"results":[105],"with":[106],"traditional":[107],"models":[108],"that":[109],"use":[110,133],"LSTM's":[111],"Neural":[114],"Networks(RNN's).":[115],"We":[116,132],"train":[117],"test":[119],"our":[120],"standard":[124],"MSVD":[125],"(Microsoft":[126],"Research":[127],"Description":[129],"Corpus)":[130],"dataset.":[131],"wide":[135],"range":[136],"performance":[138],"metrics":[139],"like":[140],"BLEU":[141],"score,":[142,144],"METEOR":[143],"ROUGE-1,":[145],"ROUGE-2":[146],"ROUGE-L":[148],"evaluate":[150],"performance.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}