{"id":"https://openalex.org/W7138036933","doi":"https://doi.org/10.1609/aaai.v40i14.38180","title":"Tell as You Want: Customizing Image Narrative with Knowledge and Thoughts","display_name":"Tell as You Want: Customizing Image Narrative with Knowledge and Thoughts","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138036933","doi":"https://doi.org/10.1609/aaai.v40i14.38180"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i14.38180","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38180","pdf_url":null,"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://doi.org/10.1609/aaai.v40i14.38180","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101931697","display_name":"Ziwei Yao","orcid":"https://orcid.org/0009-0000-4854-8217"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Yao","raw_affiliation_strings":["Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129668587","display_name":"Qian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wang","raw_affiliation_strings":["Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653067","display_name":"Ruiping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiping Wang","raw_affiliation_strings":["Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129692017","display_name":"Xilin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China\nUniversity of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11928","last_page":"11936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.98089998960495,"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":0.98089998960495,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007400000002235174,"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/T10028","display_name":"Topic Modeling","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9699000120162964},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.7163000106811523},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6359999775886536},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.616599977016449},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5835000276565552},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5666000247001648},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5259000062942505},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49729999899864197}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9699000120162964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692000269889832},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.7163000106811523},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6359999775886536},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.616599977016449},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33500000834465027},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i14.38180","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38180","pdf_url":null,"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/38180","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38180","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.v40i14.38180","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38180","pdf_url":null,"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":[{"display_name":"Quality Education","score":0.7134032249450684,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,14,29,92,111,135,156,161,173,192,205],"advancement":[2],"of":[3,16,52,94,140],"vision-language":[4],"models,":[5],"image":[6,23,95,119,136,186,209],"captioning":[7,24],"has":[8],"made":[9],"significant":[10],"progress,":[11],"leading":[12],"to":[13,100,110,155,171,195],"generation":[15,121,174,235],"more":[17],"accurate":[18,182],"and":[19,64,130,137,144,168,183,199,216],"detailed":[20],"descriptions.":[21],"Current":[22],"primarily":[25],"focuses":[26],"on":[27],"describing":[28],"apparent":[30],"visual":[31,53],"characteristics,":[32],"which":[33,98],"are":[34,153],"easily":[35],"observed":[36],"by":[37,177],"most":[38],"humans,":[39],"but":[40],"less":[41],"helpful":[42],"in":[43,220,236],"real-world":[44],"scenarios.":[45],"When":[46],"users":[47],"seek":[48],"a":[49,79,229],"deeper":[50],"understanding":[51],"content,":[54],"they":[55],"may":[56],"be":[57],"concerned":[58],"with":[59],"fine-grained":[60],"categories,":[61],"function":[62],"properties,":[63],"other":[65],"background":[66],"knowledge,":[67],"rather":[68],"than":[69],"merely":[70],"appearances.":[71],"Additionally,":[72],"as":[73,142],"users'":[74],"interests":[75],"vary,":[76],"there":[77],"is":[78],"growing":[80],"demand":[81],"for":[82,106,232],"customizable":[83],"content":[84,234],"generation.":[85],"To":[86],"address":[87],"these":[88],"challenges,":[89],"we":[90,115,190],"propose":[91,116],"task":[93,197],"narrative":[96,120],"generation,":[97],"aims":[99],"produce":[101],"knowledge-rich":[102],"natural":[103],"language":[104],"responses":[105],"input":[107],"images,":[108],"customized":[109,233],"user":[112,157,214],"preference.":[113],"Furthermore,":[114],"T^4,":[117],"an":[118,181],"model":[122,162],"progressing":[123],"through":[124,166],"cascade":[125],"steps:":[126],"Tailor,":[127],"reTrieve,":[128],"Think,":[129],"Tell.":[131],"Specifically,":[132],"it":[133],"takes":[134],"various":[138],"types":[139],"prompts":[141],"input,":[143],"first":[145],"refines":[146],"or":[147],"predicts":[148],"potentially":[149],"interesting":[150],"queries":[151],"that":[152,204,211],"tailored":[154],"expertise":[158],"level.":[159],"Subsequently,":[160],"enriches":[163],"contextual":[164],"knowledge":[165],"retrieval-augmentation":[167],"employs":[169],"chain-of-thoughts":[170],"decompose":[172],"process":[175],"step":[176],"step,":[178],"thereby":[179],"telling":[180],"logically":[184],"coherent":[185],"narrative.":[187],"In":[188],"addition,":[189],"construct":[191],"ImgNarr-23K":[193],"dataset":[194],"support":[196],"training":[198],"evaluation.":[200],"Experimental":[201],"results":[202],"demonstrate":[203],"proposed":[206],"approach":[207],"generates":[208],"narratives":[210],"better":[212],"satisfy":[213],"requirements,":[215],"achieves":[217],"state-of-the-art":[218],"performance":[219],"knowledge-based":[221],"VQA":[222],"tasks":[223],"without":[224],"additional":[225],"finetuning.":[226],"T^4":[227],"presents":[228],"promising":[230],"solution":[231],"specialized":[237],"domains.":[238]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}