{"id":"https://openalex.org/W7130594781","doi":"https://doi.org/10.1109/ictc66702.2025.11387993","title":"Development of mask guided visual effect generation with generative AI","display_name":"Development of mask guided visual effect generation with generative AI","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130594781","doi":"https://doi.org/10.1109/ictc66702.2025.11387993"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11387993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11387993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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/A5111207999","display_name":"IlHong Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"IlHong Shin","raw_affiliation_strings":["Electronics and Telecommunication Research Institute,Media Intellectualization Research Section,Daejeon,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunication Research Institute,Media Intellectualization Research Section,Daejeon,South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112268563","display_name":"Jeong-Woo Son","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeong-Woo Son","raw_affiliation_strings":["Electronics and Telecommunication Research Institute,Media Intellectualization Research Section,Daejeon,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunication Research Institute,Media Intellectualization Research Section,Daejeon,South Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"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":null,"issue":null,"first_page":"33","last_page":"34"},"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":0.7935000061988831,"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":0.7935000061988831,"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":0.046300001442432404,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01590000092983246,"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/generative-grammar","display_name":"Generative grammar","score":0.7257999777793884},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44620001316070557},{"id":"https://openalex.org/keywords/development","display_name":"Development (topology)","score":0.3578000068664551},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29420000314712524},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.29109999537467957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601000070571899},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7257999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537999868392944},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44620001316070557},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3709999918937683},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.2840999960899353}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11387993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11387993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4512060582637787,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4386057725"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"a":[5,76],"mask-guided":[6],"generative":[7],"AI":[8],"system":[9,65],"for":[10,79],"controllable":[11],"visual":[12],"effects":[13,30],"(VFX)":[14],"video":[15,83],"synthesis":[16],"based":[17],"on":[18],"latent":[19],"diffusion.":[20],"Users":[21],"can":[22],"provide":[23],"spatial":[24,50],"masks":[25],"to":[26,36,47],"define":[27],"where":[28],"the":[29,38,64],"appear":[31],"and":[32,51,56,81],"optional":[33],"text":[34],"prompts":[35],"describe":[37],"effect\u2019s":[39],"style":[40],"or":[41],"semantics.":[42],"The":[43],"model":[44],"is":[45],"fine-tuned":[46],"integrate":[48],"both":[49],"textual":[52],"conditions,":[53],"enabling":[54],"precise":[55],"realistic":[57],"effect":[58],"generation.":[59],"Experimental":[60],"results":[61],"demonstrate":[62],"that":[63],"effectively":[66],"generates":[67],"high-quality,":[68],"localized":[69],"VFX":[70],"aligned":[71],"with":[72],"user":[73],"intent,":[74],"offering":[75],"powerful":[77],"tool":[78],"intuitive":[80],"automated":[82],"editing":[84],"workflows.":[85]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}
