{"id":"https://openalex.org/W4403780694","doi":"https://doi.org/10.1145/3664647.3681533","title":"Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source Supervision","display_name":"Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source Supervision","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780694","doi":"https://doi.org/10.1145/3664647.3681533"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681533","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5072904443","display_name":"Shengguang Wu","orcid":null},"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":"Shengguang Wu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-2453-9901","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114215745","display_name":"Zhenglun Chen","orcid":null},"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":"Zhenglun Chen","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6902-1195","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066310925","display_name":"Qi Su","orcid":"https://orcid.org/0000-0002-4769-2812"},"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":"Qi Su","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4769-2812","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"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":"2719","last_page":"2728"},"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":0.9908999800682068,"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":0.9908999800682068,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9876000285148621,"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/artifact","display_name":"Artifact (error)","score":0.8383970260620117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6866708993911743},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4419044256210327},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4291146397590637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39052170515060425}],"concepts":[{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.8383970260620117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866708993911743},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4419044256210327},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4291146397590637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39052170515060425}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681533","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2145023731","https://openalex.org/W2913688275","https://openalex.org/W2962785568","https://openalex.org/W2982212456","https://openalex.org/W3127724266","https://openalex.org/W3153469116","https://openalex.org/W3173038784","https://openalex.org/W3207553988","https://openalex.org/W4286238648","https://openalex.org/W4304014146","https://openalex.org/W4312933868","https://openalex.org/W4320736349","https://openalex.org/W4385572634","https://openalex.org/W4390873030"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Ancient":[0],"artifacts":[1,16],"are":[2,17],"an":[3],"important":[4,53],"medium":[5],"for":[6,33],"cultural":[7],"preservation":[8],"and":[9,28,73,105,152,186,201],"restoration.":[10],"However,":[11],"many":[12],"physical":[13],"copies":[14],"of":[15,61,165],"either":[18],"damaged":[19],"or":[20],"lost,":[21],"leaving":[22],"a":[23,80,99,141],"blank":[24],"space":[25],"in":[26,43,57,64,66,140,202],"archaeological":[27,122],"historical":[29,90,138,187],"studies":[30],"that":[31,87,155,179],"calls":[32],"techniques":[34,109],"to":[35,50,110,136,159,169],"re-visualize":[36],"these":[37],"artifacts.":[38,167],"Despite":[39],"the":[40,52,58,112,166,183],"significant":[41,195],"advancements":[42],"open-domain":[44],"text-to-image":[45,113],"synthesis,":[46],"existing":[47,170],"approaches":[48],"fail":[49],"capture":[51],"domain":[54],"knowledge":[55,123,188],"presented":[56],"textual":[59,134],"descriptions":[60],"artifacts,":[62],"resulting":[63],"errors":[65],"recreated":[67],"images":[68,178],"such":[69],"as":[70,103],"incorrect":[71],"shapes":[72],"patterns.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,117,131,145],"propose":[79],"novel":[81],"knowledge-aware":[82],"artifact":[83,177],"image":[84],"synthesis":[85],"approach":[86],"brings":[88],"lost":[89],"objects":[91],"accurately":[92],"into":[93],"their":[94],"visual":[95,163],"forms.":[96],"We":[97],"use":[98],"pretrained":[100],"diffusion":[101],"model":[102,158,174],"backbone":[104],"introduce":[106,146],"three":[107],"key":[108],"enhance":[111],"generation":[114],"framework:":[115],"1)":[116],"construct":[118],"prompts":[119],"with":[120,182],"explicit":[121],"elicited":[124],"from":[125],"large":[126],"language":[127],"models":[128],"(LLMs);":[129],"2)":[130],"incorporate":[132],"additional":[133],"guidance":[135],"correlated":[137],"expertise":[139],"contrastive":[142],"manner;":[143],"3)":[144],"further":[147],"visual-semantic":[148],"constraints":[149],"on":[150],"edge":[151],"perceptual":[153],"features":[154],"enable":[156],"our":[157,172],"learn":[160],"more":[161],"intricate":[162],"details":[164,185],"Compared":[168],"approaches,":[171],"proposed":[173],"produces":[175],"higher-quality":[176],"align":[180],"better":[181],"implicit":[184],"contained":[189],"within":[190],"written":[191],"documents,":[192],"thus":[193],"achieving":[194],"improvements":[196],"both":[197],"across":[198],"automatic":[199],"metrics":[200],"human":[203],"evaluation.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}