{"id":"https://openalex.org/W2963668753","doi":"https://doi.org/10.1609/aaai.v33i01.33018465","title":"Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation","display_name":"Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963668753","doi":"https://doi.org/10.1609/aaai.v33i01.33018465","mag":"2963668753"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4863/4736","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4863/4736","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102459817","display_name":"Qiuyuan Huang","orcid":"https://orcid.org/0000-0003-1421-9698"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiuyuan Huang","raw_affiliation_strings":["Microsoft Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research AI","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066666034","display_name":"Zhe Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhe Gan","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030468199","display_name":"Asl\u0131 \u00c7eliky\u0131lmaz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Asli Celikyilmaz","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001469325","display_name":"Dapeng Wu","orcid":"https://orcid.org/0000-0003-1755-0183"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dapeng Wu","raw_affiliation_strings":["University of Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358523","display_name":"Jianfeng Wang","orcid":"https://orcid.org/0000-0003-0932-3060"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Wang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["JD AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":95,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"8465","last_page":"8472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.98580002784729,"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":0.9751999974250793,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8263483643531799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779590368270874},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7119081616401672},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6763867735862732},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.6373440623283386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6136065125465393},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.568183958530426},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4917888939380646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4124809503555298},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.09026932716369629},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0721653401851654}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8263483643531799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779590368270874},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7119081616401672},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6763867735862732},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.6373440623283386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136065125465393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.568183958530426},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4917888939380646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4124809503555298},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.09026932716369629},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0721653401851654},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4863/4736","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4863","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018465","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018465","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4863/4736","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963668753.pdf","grobid_xml":"https://content.openalex.org/works/W2963668753.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1573040851","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1957740064","https://openalex.org/W2019781059","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2176263492","https://openalex.org/W2183386595","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2273041409","https://openalex.org/W2506483933","https://openalex.org/W2508429489","https://openalex.org/W2525778437","https://openalex.org/W2542835211","https://openalex.org/W2549599535","https://openalex.org/W2558834163","https://openalex.org/W2559780844","https://openalex.org/W2560313346","https://openalex.org/W2607151106","https://openalex.org/W2612675303","https://openalex.org/W2742943414","https://openalex.org/W2744208073","https://openalex.org/W2768287968","https://openalex.org/W2770168862","https://openalex.org/W2775506363","https://openalex.org/W2794945088","https://openalex.org/W2798353932","https://openalex.org/W2949376505","https://openalex.org/W2950304420","https://openalex.org/W2962937869","https://openalex.org/W2963033554","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963187786","https://openalex.org/W2963385935","https://openalex.org/W2963843052","https://openalex.org/W2963916161","https://openalex.org/W2964222573","https://openalex.org/W4230563027","https://openalex.org/W4294149591","https://openalex.org/W6639657675","https://openalex.org/W6666761814","https://openalex.org/W6680375555","https://openalex.org/W6682631176","https://openalex.org/W6687483927","https://openalex.org/W6691431627","https://openalex.org/W6737009557","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2884441370","https://openalex.org/W1536421369","https://openalex.org/W2082193010","https://openalex.org/W4319988281","https://openalex.org/W2086118318","https://openalex.org/W2993120730","https://openalex.org/W1765898938","https://openalex.org/W2970945984","https://openalex.org/W2355818213","https://openalex.org/W4320006770"],"abstract_inverted_index":{"We":[0,97],"propose":[1],"a":[2,31,34,41,49,53,67,73,129],"hierarchically":[3,119],"structured":[4,120],"reinforcement":[5,95,133],"learning":[6,134],"approach":[7],"to":[8,128],"address":[9],"the":[10,20,27,80,85,102,117],"challenges":[11],"of":[12,29,36],"planning":[13],"for":[14,19,58,69],"generating":[15,30,52],"coherent":[16],"multi-sentence":[17],"stories":[18],"visual":[21,103],"storytelling":[22,104],"task.":[23],"Within":[24],"our":[25,99],"framework,":[26],"task":[28],"story":[32],"given":[33],"sequence":[35],"images":[37],"is":[38],"divided":[39],"across":[40],"two-level":[42],"hierarchical":[43],"decoder.":[44],"The":[45,63,87],"high-level":[46],"decoder":[47,65],"constructs":[48],"plan":[50],"by":[51],"semantic":[54,74],"concept":[55],"(i.e.,":[56],"topic)":[57],"each":[59,70],"image":[60,71],"in":[61],"sequence.":[62],"low-level":[64],"generates":[66],"sentence":[68,81],"using":[72,94],"compositional":[75],"network,":[76],"which":[77],"effectively":[78],"grounds":[79],"generation":[82],"conditioned":[83],"on":[84,101],"topic.":[86],"two":[88],"decoders":[89],"are":[90],"jointly":[91],"trained":[92],"end-to-end":[93],"learning.":[96],"evaluate":[98],"model":[100],"(VIST)":[105],"dataset.":[106],"Empirical":[107],"results":[108],"from":[109],"both":[110],"automatic":[111],"and":[112],"human":[113],"evaluations":[114],"demonstrate":[115],"that":[116],"proposed":[118],"reinforced":[121],"training":[122],"achieves":[123],"significantly":[124],"better":[125],"performance":[126],"compared":[127],"strong":[130],"flat":[131],"deep":[132],"baseline.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":20}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}