{"id":"https://openalex.org/W3082226086","doi":"https://doi.org/10.1109/tcsvt.2020.3020877","title":"Hierarchical Memory Decoder for Visual Narrating","display_name":"Hierarchical Memory Decoder for Visual Narrating","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W3082226086","doi":"https://doi.org/10.1109/tcsvt.2020.3020877","mag":"3082226086"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2020.3020877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3020877","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","Tianjin Key Laboratory of Machine Learning, 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"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Machine Learning, 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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahong Han","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China","Peng Cheng Laboratory, Shenzhen, China","Tianjin Key Laboratory of Machine Learning, 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"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Machine Learning, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"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":"Zhou Zhao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0542,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79549526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"31","issue":"6","first_page":"2438","last_page":"2449"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"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":0.9976000189781189,"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":0.8648602366447449},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6788939237594604},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5035189986228943},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46283864974975586},{"id":"https://openalex.org/keywords/visual-memory","display_name":"Visual memory","score":0.4416179955005646},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4303989112377167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3858204483985901},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.23683017492294312},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14880067110061646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12696793675422668},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.08938008546829224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8648602366447449},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6788939237594604},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5035189986228943},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46283864974975586},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.4416179955005646},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4303989112377167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3858204483985901},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.23683017492294312},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14880067110061646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12696793675422668},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.08938008546829224},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2020.3020877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3020877","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":96,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1793121960","https://openalex.org/W1895577753","https://openalex.org/W1924770834","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2098774185","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2164290393","https://openalex.org/W2176091656","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2318631040","https://openalex.org/W2343553806","https://openalex.org/W2425121537","https://openalex.org/W2430148947","https://openalex.org/W2554906389","https://openalex.org/W2557264465","https://openalex.org/W2566467060","https://openalex.org/W2580175322","https://openalex.org/W2613904329","https://openalex.org/W2621571501","https://openalex.org/W2740388348","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2766711654","https://openalex.org/W2768287968","https://openalex.org/W2777622844","https://openalex.org/W2808203533","https://openalex.org/W2808647806","https://openalex.org/W2889418103","https://openalex.org/W2951008357","https://openalex.org/W2951390634","https://openalex.org/W2953318193","https://openalex.org/W2953333557","https://openalex.org/W2953486038","https://openalex.org/W2962681491","https://openalex.org/W2962694510","https://openalex.org/W2962845991","https://openalex.org/W2962861647","https://openalex.org/W2962907269","https://openalex.org/W2962941628","https://openalex.org/W2962958773","https://openalex.org/W2963033554","https://openalex.org/W2963119563","https://openalex.org/W2963149042","https://openalex.org/W2963187786","https://openalex.org/W2963277051","https://openalex.org/W2963383024","https://openalex.org/W2963403868","https://openalex.org/W2963508354","https://openalex.org/W2963576560","https://openalex.org/W2963668753","https://openalex.org/W2963843052","https://openalex.org/W2963971014","https://openalex.org/W2964241990","https://openalex.org/W2964265128","https://openalex.org/W2965846473","https://openalex.org/W2981411942","https://openalex.org/W2981750519","https://openalex.org/W3007773043","https://openalex.org/W3087871082","https://openalex.org/W3098682680","https://openalex.org/W3100995281","https://openalex.org/W3103559770","https://openalex.org/W3123212791","https://openalex.org/W4285719527","https://openalex.org/W4385245566","https://openalex.org/W6638318767","https://openalex.org/W6640212811","https://openalex.org/W6674884181","https://openalex.org/W6679436768","https://openalex.org/W6680145277","https://openalex.org/W6684090549","https://openalex.org/W6685670348","https://openalex.org/W6717888560","https://openalex.org/W6718092244","https://openalex.org/W6731259203","https://openalex.org/W6732665253","https://openalex.org/W6732742072","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6744591284","https://openalex.org/W6745347688","https://openalex.org/W6746421592","https://openalex.org/W6747016466","https://openalex.org/W6749210505","https://openalex.org/W6754546032","https://openalex.org/W6765069029","https://openalex.org/W6765766786","https://openalex.org/W6774244609"],"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":{"Visual":[0],"narrating":[1],"focuses":[2],"on":[3,147,252],"generating":[4,247],"semantic":[5],"descriptions":[6,34],"to":[7,27,31,59,124,138,172,182,188,199,219],"summarize":[8],"visual":[9,16,19,36,96,121,141,256,262],"content":[10],"of":[11,67,81,105,159,204,229,240,255,276],"images":[12],"or":[13],"videos,":[14],"e.g.,":[15,47],"captioning":[17,260],"and":[18,142,177,213,261,272],"storytelling.":[20],"The":[21,98],"challenge":[22],"mainly":[23],"lies":[24],"in":[25,164],"how":[26],"design":[28,132],"a":[29,42,116,126,133,155,169,196],"decoder":[30,119,157,226,267],"generate":[32],"accurate":[33,248],"matching":[35],"content.":[37],"Recent":[38,71],"advances":[39],"often":[40],"employ":[41,168,195],"recurrent":[43],"neural":[44],"network":[45,76],"(RNN),":[46],"Long-Short":[48],"Term":[49],"Memory":[50],"(LSTM),":[51],"as":[52,86],"the":[53,79,87,103,148,185,189,201,209,221,233,237,274],"decoder.":[54,279],"However,":[55,85],"RNN":[56],"is":[57,244],"prone":[58],"diluting":[60],"long-term":[61,69,83,230],"information,":[62],"which":[63,243],"weakens":[64],"its":[65],"performance":[66,275],"capturing":[68],"dependencies.":[70],"work":[72],"has":[73,90],"demonstrated":[74],"memory":[75,118,161,170,197,206],"(MemNet)":[77],"owns":[78],"advantage":[80],"storing":[82],"information.":[84,144,223,231],"decoder,":[88],"it":[89],"not":[91],"been":[92],"well":[93],"exploited":[94],"for":[95,120,246],"narrating.":[97,122],"reason":[99],"partially":[100],"comes":[101],"from":[102],"difficulty":[104],"multi-modal":[106,128,135],"sequential":[107],"decoding":[108,175,202],"with":[109],"MemNet.":[110],"In":[111],"this":[112,225],"article,":[113],"we":[114,130,153,167,193],"devise":[115],"novel":[117],"Concretely,":[123],"obtain":[125,269],"better":[127],"representation,":[129],"first":[131],"new":[134],"fusion":[136,149],"method":[137],"fully":[139],"merge":[140],"lexical":[143],"Then,":[145],"based":[146],"result,":[150],"during":[151],"decoding,":[152],"construct":[154],"MemNet-based":[156],"consisting":[158],"multiple":[160],"layers.":[162],"Particularly,":[163],"each":[165,205,241],"layer,":[166,242],"set":[171,198],"store":[173,200],"previous":[174],"information":[176,186,239],"utilize":[178,215],"an":[179,216],"attention":[180,217],"mechanism":[181,218],"adaptively":[183],"select":[184,220],"related":[187,222],"current":[190,210],"output.":[191],"Meanwhile,":[192,232],"also":[194],"output":[203],"layer":[207],"at":[208],"time":[211],"step":[212],"still":[214],"Thus,":[224],"alleviates":[227],"dilution":[228],"hierarchical":[234],"architecture":[235],"leverages":[236],"latent":[238],"helpful":[245],"descriptions.":[249],"Experimental":[250],"results":[251,271],"two":[253],"tasks":[254],"narrating,":[257],"i.e.,":[258],"video":[259],"storytelling,":[263],"show":[264],"that":[265],"our":[266],"could":[268],"superior":[270],"outperform":[273],"conventional":[277],"RNN-based":[278]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}