{"id":"https://openalex.org/W4415707942","doi":"https://doi.org/10.1109/icme59968.2025.11210189","title":"Object Isolated Attention for Consistent Story Visualization","display_name":"Object Isolated Attention for Consistent Story Visualization","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707942","doi":"https://doi.org/10.1109/icme59968.2025.11210189"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5109423417","display_name":"Xiangyang Luo","orcid":"https://orcid.org/0009-0001-2828-387X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Luo","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101448179","display_name":"Junhao Cheng","orcid":"https://orcid.org/0000-0001-8567-0158"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Cheng","raw_affiliation_strings":["Sun Yat-sen University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,Shenzhen,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056844117","display_name":"Yifan Xie","orcid":"https://orcid.org/0009-0002-3225-9220"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Xie","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108313260","display_name":"Xin Zhang","orcid":"https://orcid.org/0009-0004-7590-8600"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074720440","display_name":"Tao Feng","orcid":"https://orcid.org/0000-0003-2977-1530"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Feng","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Liu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031311274","display_name":"Fei Ma","orcid":"https://orcid.org/0009-0002-5388-9125"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Ma","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85146628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.5752000212669373,"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":0.5752000212669373,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1264999955892563,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.07329999655485153,"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/visualization","display_name":"Visualization","score":0.6359000205993652},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6150000095367432},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5317000150680542},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44119998812675476},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43779999017715454},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4302000105381012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771399974822998},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6359000205993652},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5866000056266785},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43779999017715454},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30169999599456787},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C3018587665","wikidata":"https://www.wikidata.org/wiki/Q7268696","display_name":"Qualitative analysis","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C14669888","wikidata":"https://www.wikidata.org/wiki/Q4014850","display_name":"Creative visualization","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2015319117","https://openalex.org/W2963047368","https://openalex.org/W4312933868","https://openalex.org/W4380881106","https://openalex.org/W4385573943","https://openalex.org/W4386076676","https://openalex.org/W4389574988","https://openalex.org/W4390872297","https://openalex.org/W4394593186","https://openalex.org/W4400818431","https://openalex.org/W4402623742","https://openalex.org/W4402703034","https://openalex.org/W4402726936","https://openalex.org/W4402774246","https://openalex.org/W4403780774","https://openalex.org/W4403877777","https://openalex.org/W4404612908","https://openalex.org/W4409263229","https://openalex.org/W4409366558","https://openalex.org/W4412795914","https://openalex.org/W4413319148"],"related_works":[],"abstract_inverted_index":{"Open-ended":[0],"story":[1],"visualization":[2],"is":[3,22,116],"a":[4,14],"challenging":[5],"task":[6],"that":[7,48,135],"involves":[8],"generating":[9],"coherent":[10],"image":[11],"sequences":[12],"from":[13,60],"given":[15],"storyline.":[16],"One":[17],"of":[18,91,122],"the":[19,92,96,119],"main":[20],"difficulties":[21],"maintaining":[23],"character":[24,75],"consistency":[25,76],"while":[26],"creating":[27],"natural":[28],"and":[29,53,87,109,125,131],"contextually":[30],"fitting":[31],"scenes\u2014an":[32],"area":[33],"where":[34],"many":[35],"existing":[36],"methods":[37],"struggle.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"an":[44],"enhanced":[45],"Transformer":[46],"module":[47],"uses":[49],"separate":[50],"self":[51,71],"attention":[52,55,72,79,99],"cross":[54,98],"mechanisms,":[56],"leveraging":[57],"prior":[58],"knowledge":[59],"pre-trained":[61],"diffusion":[62],"models":[63],"to":[64,81],"ensure":[65],"logical":[66],"scene":[67],"creation.":[68],"The":[69],"isolated":[70,97],"mechanism":[73,100],"improves":[74],"by":[77],"refining":[78],"maps":[80],"reduce":[82],"focus":[83],"on":[84],"irrelevant":[85],"areas":[86],"highlight":[88],"key":[89],"features":[90],"same":[93],"character.":[94],"Meanwhile,":[95],"independently":[101],"processes":[102],"each":[103],"character\u2019s":[104],"features,":[105],"avoiding":[106],"feature":[107],"fusion":[108],"further":[110],"strengthening":[111],"consistency.":[112],"Notably,":[113],"our":[114,136],"method":[115],"training-free,":[117],"allowing":[118],"continuous":[120],"generation":[121],"new":[123],"characters":[124],"storylines":[126],"without":[127],"re-tuning.":[128],"Both":[129],"qualitative":[130],"quantitative":[132],"evaluations":[133],"show":[134],"approach":[137],"outperforms":[138],"current":[139],"methods,":[140],"demonstrating":[141],"its":[142],"effectiveness.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}