{"id":"https://openalex.org/W2966774251","doi":"https://doi.org/10.24963/ijcai.2019/744","title":"Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling","display_name":"Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966774251","doi":"https://doi.org/10.24963/ijcai.2019/744","mag":"2966774251"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/744","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/744","pdf_url":"https://www.ijcai.org/proceedings/2019/0744.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0744.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063385901","display_name":"Pengcheng Yang","orcid":"https://orcid.org/0000-0001-8671-9523"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengcheng Yang","raw_affiliation_strings":["Deep Learning Lab, Beijing Institute of Big Data Research, Peking University","MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"Deep Learning Lab, Beijing Institute of Big Data Research, Peking University","institution_ids":["https://openalex.org/I4210096250","https://openalex.org/I20231570"]},{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019525050","display_name":"Fuli Luo","orcid":"https://orcid.org/0000-0002-5403-6434"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuli Luo","raw_affiliation_strings":["MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399209","display_name":"Peng Chen","orcid":"https://orcid.org/0000-0003-2427-5116"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Chen","raw_affiliation_strings":["MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083290750","display_name":"Zhiyi Yin","orcid":"https://orcid.org/0000-0001-8334-3233"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Yin","raw_affiliation_strings":["MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["JD AI Research, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Sun","raw_affiliation_strings":["Deep Learning Lab, Beijing Institute of Big Data Research, Peking University","MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"Deep Learning Lab, Beijing Institute of Big Data Research, Peking University","institution_ids":["https://openalex.org/I4210096250","https://openalex.org/I20231570"]},{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5063385901"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210096250"],"apc_list":null,"apc_paid":null,"fwci":3.3701,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.94108993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5356","last_page":"5362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9947999715805054,"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/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.8575931191444397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7771648168563843},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.7228071689605713},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.66254723072052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4888290762901306},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44772204756736755},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4091663956642151},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35751649737358093},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.12565112113952637},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11102461814880371}],"concepts":[{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.8575931191444397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771648168563843},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.7228071689605713},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.66254723072052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4888290762901306},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44772204756736755},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4091663956642151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35751649737358093},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.12565112113952637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11102461814880371},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.24963/ijcai.2019/744","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/744","pdf_url":"https://www.ijcai.org/proceedings/2019/0744.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/744","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/744","pdf_url":"https://www.ijcai.org/proceedings/2019/0744.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7215211584","display_name":null,"funder_award_id":"61673028","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966774251.pdf","grobid_xml":"https://content.openalex.org/works/W2966774251.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250770256","https://openalex.org/W2738134019","https://openalex.org/W2768287968","https://openalex.org/W2804668597","https://openalex.org/W2805389239","https://openalex.org/W2807346103","https://openalex.org/W2888213795","https://openalex.org/W2889002152","https://openalex.org/W2949847915","https://openalex.org/W2963033554","https://openalex.org/W2963096510","https://openalex.org/W2963187786","https://openalex.org/W2963248507","https://openalex.org/W2963351776","https://openalex.org/W2963373848","https://openalex.org/W2963668753","https://openalex.org/W2963978266","https://openalex.org/W2963993699","https://openalex.org/W2964308564","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"The":[0],"visual":[1,102],"storytelling":[2],"(VST)":[3],"task":[4,38],"aims":[5,91],"at":[6],"generating":[7],"a":[8,25,73,86,108,167,172],"reasonable":[9,74],"and":[10,27,60,182,192],"coherent":[11],"paragraph-level":[12],"story":[13,34,75],"with":[14,62],"the":[15,33,36,51,55,63,77,97,115,131,140,144,150,153,163,186],"image":[16,31,78],"stream":[17],"as":[18],"input.":[19],"Different":[20],"from":[21,96,114],"caption":[22],"that":[23,46,158],"is":[24,126],"direct":[26],"literal":[28],"description":[29],"of":[30,43,110,152,176],"content,":[32],"in":[35,50,81],"VST":[37],"tends":[39],"to":[40,58,71,92,128,138,148],"contain":[41],"plenty":[42],"imaginary":[44,64],"concepts":[45,65],"do":[47],"not":[48],"appear":[49],"image.":[52],"This":[53],"requires":[54],"AI":[56],"agent":[57],"reason":[59],"associate":[61],"based":[66,184],"on":[67],"implicit":[68],"commonsense":[69,95,181],"knowledge":[70,99,112,116],"generate":[72],"describing":[76],"stream.":[79],"Therefore,":[80],"this":[82],"work,":[83],"we":[84,136],"present":[85],"commonsense-driven":[87],"generative":[88],"model,":[89],"which":[90,170],"introduce":[93],"crucial":[94],"external":[98],"base":[100],"for":[101],"storytelling.":[103],"Our":[104],"approach":[105,160],"first":[106],"extracts":[107],"set":[109],"candidate":[111],"graphs":[113],"base.":[117],"Then,":[118],"an":[119],"elaborately":[120],"designed":[121],"vision-aware":[122],"directional":[123],"encoding":[124],"schema":[125],"adopted":[127],"effectively":[129],"integrate":[130],"most":[132],"informative":[133],"commonsense.":[134],"Besides,":[135],"strive":[137],"maximize":[139],"semantic":[141],"similarity":[142],"within":[143],"output":[145],"during":[146],"decoding":[147],"enhance":[149],"coherence":[151],"generated":[154,187],"text.":[155],"Results":[156],"show":[157],"our":[159],"can":[161],"outperform":[162],"state-of-the-art":[164],"systems":[165],"by":[166],"large":[168],"margin,":[169],"achieves":[171],"29\\%":[173],"relative":[174],"improvement":[175],"CIDEr":[177],"score.":[178],"With":[179],"additional":[180],"semantic-relevance":[183],"objective,":[185],"stories":[188],"are":[189],"more":[190],"diverse":[191],"coherent.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}