{"id":"https://openalex.org/W4292263758","doi":"https://doi.org/10.1109/tcsvt.2022.3199603","title":"Coherent Visual Storytelling via Parallel Top-Down Visual and Topic Attention","display_name":"Coherent Visual Storytelling via Parallel Top-Down Visual and Topic Attention","publication_year":2022,"publication_date":"2022-08-17","ids":{"openalex":"https://openalex.org/W4292263758","doi":"https://doi.org/10.1109/tcsvt.2022.3199603"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3199603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3199603","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/A5057852825","display_name":"Jinjing Gu","orcid":"https://orcid.org/0000-0002-7669-8201"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjing Gu","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China","Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9999-4871","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061965819","display_name":"Ruichao Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichao Fan","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.648,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.655947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"33","issue":"1","first_page":"257","last_page":"268"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9961000084877014,"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":0.9811000227928162,"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":0.7108006477355957},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.6198920011520386},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5565026998519897},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.47935324907302856},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.46029341220855713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44628167152404785},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.4454723000526428},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4424607753753662},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.4288322329521179},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37496012449264526},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3584122657775879},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.26599258184432983},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2468544840812683},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15897855162620544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7108006477355957},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6198920011520386},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5565026998519897},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.47935324907302856},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.46029341220855713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44628167152404785},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.4454723000526428},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4424607753753662},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.4288322329521179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37496012449264526},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3584122657775879},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.26599258184432983},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2468544840812683},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15897855162620544},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3199603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3199603","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G4201522284","display_name":null,"funder_award_id":"52102382","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5501368935","display_name":null,"funder_award_id":"61976159","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":67,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2001082470","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2222235228","https://openalex.org/W2250533720","https://openalex.org/W2302086703","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2575842049","https://openalex.org/W2584271190","https://openalex.org/W2605045867","https://openalex.org/W2625940279","https://openalex.org/W2741196623","https://openalex.org/W2745461083","https://openalex.org/W2766711654","https://openalex.org/W2795151422","https://openalex.org/W2804668597","https://openalex.org/W2807346103","https://openalex.org/W2808663243","https://openalex.org/W2883891001","https://openalex.org/W2888321701","https://openalex.org/W2890531016","https://openalex.org/W2949555952","https://openalex.org/W2953486038","https://openalex.org/W2963033554","https://openalex.org/W2963187786","https://openalex.org/W2963668753","https://openalex.org/W2963811641","https://openalex.org/W2963829244","https://openalex.org/W2964546107","https://openalex.org/W2965112138","https://openalex.org/W2966774251","https://openalex.org/W2987862245","https://openalex.org/W2996941455","https://openalex.org/W2998106530","https://openalex.org/W2998303222","https://openalex.org/W2998559045","https://openalex.org/W2998813101","https://openalex.org/W3036848992","https://openalex.org/W3048921104","https://openalex.org/W3082226086","https://openalex.org/W3087871082","https://openalex.org/W3094176136","https://openalex.org/W3100995281","https://openalex.org/W3103668594","https://openalex.org/W3106477714","https://openalex.org/W3113632293","https://openalex.org/W3128339783","https://openalex.org/W3131251978","https://openalex.org/W3132408010","https://openalex.org/W3134875898","https://openalex.org/W3136792391","https://openalex.org/W3162694035","https://openalex.org/W3173770572","https://openalex.org/W3176313262","https://openalex.org/W3176565349","https://openalex.org/W4243879827","https://openalex.org/W4285125423","https://openalex.org/W4288083805","https://openalex.org/W6678262379","https://openalex.org/W6682044806","https://openalex.org/W6688797756","https://openalex.org/W6728274705","https://openalex.org/W6751888654","https://openalex.org/W6752255509","https://openalex.org/W6796990549"],"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/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Visual":[0],"storytelling":[1,94],"aims":[2],"at":[3],"producing":[4],"a":[5,9,44,58,91,139,143,149,170,182,235],"narrative":[6],"paragraph":[7,22],"for":[8],"given":[10],"photo":[11,45,123],"album":[12],"automatically.":[13],"It":[14],"introduces":[15],"more":[16,236],"new":[17],"challenges":[18],"than":[19,244],"individual":[20],"image":[21,110],"descriptions,":[23],"mainly":[24],"due":[25],"to":[26,38,84,99,115,200],"the":[27,40,61,65,69,101,106,121,126,158,161,164,176,202,206,211,220],"difficulty":[28],"in":[29,34,57,105,234,268],"preserving":[30],"coherent":[31,92,150,230],"topics":[32],"and":[33,64,131,148,160,231,249,256],"generating":[35],"diverse":[36,232],"phrases":[37],"depict":[39],"rich":[41],"content":[42],"of":[43,120,163,178,205,262],"album.":[46,124],"Existing":[47],"attention-based":[48],"models":[49],"that":[50,225],"lack":[51],"higher-level":[52],"guiding":[53],"information":[54],"always":[55],"result":[56],"deviation":[59],"between":[60],"generated":[62,179,207],"sentence":[63],"topic":[66,132,167],"expressed":[67],"by":[68],"image.":[70],"In":[71,88],"addition,":[72],"these":[73],"widely":[74],"applied":[75],"language":[76,151],"generation":[77],"approaches":[78],"employing":[79],"standard":[80],"beam":[81,184],"search":[82,185],"tend":[83],"produce":[85],"monotonous":[86],"descriptions.":[87],"this":[89,263],"work,":[90],"visual":[93,118,130,154],"(CoVS)":[95],"framework":[96],"is":[97,113,136,197],"designed":[98,114,199],"address":[100],"above-mentioned":[102],"problems.":[103],"Specifically,":[104],"encoding":[107],"phase,":[108],"an":[109],"sequence":[111],"encoder":[112],"efficiently":[116],"extract":[117],"features":[119],"input":[122],"Then,":[125],"novel":[127],"parallel":[128,144],"top-down":[129,145],"attention":[133,146,155,168],"(PTDVTA)":[134],"decoder":[135],"constructed":[137],"via":[138],"topic-aware":[140,171],"neural":[141,172],"network,":[142],"model,":[147],"generator.":[152],"Concretely,":[153],"focuses":[156],"on":[157,219,247],"attributes":[159],"relationships":[162],"objects,":[165],"while":[166,252],"integrating":[169],"network":[173],"could":[174],"improve":[175],"coherence":[177],"sentences.":[180],"Eventually,":[181],"phrase":[183],"algorithm":[186],"with":[187],"<inline-formula":[188],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[189,270],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[190],"<tex-math":[191],"notation=\"LaTeX\">$n$":[192],"</tex-math></inline-formula>":[193],"-gram":[194],"hamming":[195],"diversity":[196,204],"further":[198],"optimize":[201],"expression":[203],"story.":[208],"To":[209],"justify":[210],"proposed":[212],"CoVS":[213,226,240],"framework,":[214],"extensive":[215],"experiments":[216],"are":[217],"conducted":[218],"VIST":[221],"dataset,":[222],"which":[223],"shows":[224],"can":[227,265],"automatically":[228],"generate":[229],"stories":[233],"natural":[237],"way.":[238],"Moreover,":[239],"obtains":[241],"better":[242],"performance":[243],"state-of-the-art":[245],"baselines":[246],"BLEU-4":[248],"METEOR":[250],"scores,":[251],"maintaining":[253],"good":[254],"CIDEr":[255],"ROUGH_L":[257],"scores.":[258],"The":[259],"source":[260],"code":[261],"work":[264],"be":[266],"found":[267],"<uri":[269],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://mic.tongji.edu.cn</uri>":[271],".":[272]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}