{"id":"https://openalex.org/W4408347308","doi":"https://doi.org/10.1109/icassp49660.2025.10889265","title":"Knowledge-Enhanced Poetry-Image Synthesis with Large Language Model","display_name":"Knowledge-Enhanced Poetry-Image Synthesis with Large Language Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347308","doi":"https://doi.org/10.1109/icassp49660.2025.10889265"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017749378","display_name":"Simin Yang","orcid":"https://orcid.org/0000-0001-9371-2557"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simin Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379933","display_name":"Yuqing Li","orcid":"https://orcid.org/0000-0002-2357-7107"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073512879","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0002-4217-950X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9897000193595886,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9897000193595886,"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/T12290","display_name":"Human Motion and Animation","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.958299994468689,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/poetry","display_name":"Poetry","score":0.6932200789451599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6882994174957275},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4660417139530182},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4650000333786011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4253408908843994},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1964200735092163},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.16863220930099487}],"concepts":[{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.6932200789451599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6882994174957275},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4660417139530182},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4650000333786011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4253408908843994},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1964200735092163},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.16863220930099487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2953356739","https://openalex.org/W2962785568","https://openalex.org/W2963527096","https://openalex.org/W3096831136","https://openalex.org/W4200343165","https://openalex.org/W4226076338","https://openalex.org/W4280643747","https://openalex.org/W4297676396","https://openalex.org/W4312933868","https://openalex.org/W4327620375","https://openalex.org/W4384297303","https://openalex.org/W4385573585","https://openalex.org/W4387195417","https://openalex.org/W4387968301","https://openalex.org/W4387969487","https://openalex.org/W4393148016","https://openalex.org/W4402667114","https://openalex.org/W4403840670","https://openalex.org/W4408787990","https://openalex.org/W6765779288","https://openalex.org/W6767137312","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6796559658","https://openalex.org/W6839492876","https://openalex.org/W6844194202","https://openalex.org/W6846157311","https://openalex.org/W6850625674","https://openalex.org/W6852232343","https://openalex.org/W6860990319","https://openalex.org/W6862078622","https://openalex.org/W6869164663","https://openalex.org/W6872159109"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Classical":[0],"Chinese":[1],"poetry":[2,10,39,114],"is":[3],"a":[4,77,83,88,107],"valuable":[5],"cultural":[6],"heritage.":[7],"Transforming":[8],"classical":[9,38,61,113],"into":[11,119],"visual":[12,120],"images":[13],"enriches":[14],"its":[15],"expressive":[16],"form":[17],"and":[18,44,92],"makes":[19],"it":[20],"more":[21],"accessible":[22],"to":[23,41,51,100],"modern":[24],"audiences.":[25],"While":[26],"generative":[27],"models":[28,99,102],"have":[29],"succeeded":[30],"in":[31,60,64,112,123],"text-to-image":[32],"synthesis,":[33],"existing":[34],"methods":[35,48],"struggle":[36],"with":[37,56,87],"due":[40],"data":[42],"scarcity":[43],"semantic":[45,58],"differences.":[46],"These":[47],"often":[49],"fail":[50],"capture":[52],"the":[53,67,94,109],"imagery":[54,110],"entities":[55],"ancient-modern":[57],"differences":[59],"poetry,":[62],"resulting":[63],"deviations":[65],"from":[66,96],"poem\u2019s":[68],"original":[69],"intent.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"Poem-Diffusion,":[76],"novel":[78],"knowledge-enhanced":[79],"method":[80],"that":[81],"combines":[82],"latent":[84],"diffusion":[85],"model":[86],"multimodal":[89],"knowledge":[90,95,104],"graph":[91],"transfers":[93],"large":[97],"language":[98],"smaller":[101],"through":[103],"distillation.":[105],"As":[106],"result,":[108],"embedded":[111],"can":[115],"be":[116],"accurately":[117],"converted":[118],"forms,":[121],"even":[122],"resource-constrained":[124],"environments.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}