{"id":"https://openalex.org/W4417073344","doi":"https://doi.org/10.1145/3743093.3771013","title":"EliGen: Entity-Level Controlled Image Generation with Regional Attention","display_name":"EliGen: Entity-Level Controlled Image Generation with Regional Attention","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073344","doi":"https://doi.org/10.1145/3743093.3771013"},"language":"en","primary_location":{"id":"doi:10.1145/3743093.3771013","doi":"https://doi.org/10.1145/3743093.3771013","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771013","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771013","source":{"id":"https://openalex.org/S7407087938","display_name":"ACM International Conference on Multimedia in Asia (MMAsia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100605845","display_name":"Hong Zhang","orcid":"https://orcid.org/0000-0003-4004-617X","observed_orcids":["https://orcid.org/0000-0003-4004-617X"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["Zhejiang University, hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-4004-617X","affiliations":[{"raw_affiliation_string":"Zhejiang University, hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040636331","display_name":"Zhongjie Duan","orcid":"https://orcid.org/0000-0002-5973-8240","observed_orcids":["https://orcid.org/0000-0002-5973-8240"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjie Duan","raw_affiliation_strings":["ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-5973-8240","affiliations":[{"raw_affiliation_string":"ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingjun Wang","orcid":"https://orcid.org/0000-0002-8150-4168","observed_orcids":["https://orcid.org/0000-0002-8150-4168"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjun Wang","raw_affiliation_strings":["ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-8150-4168","affiliations":[{"raw_affiliation_string":"ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042773283","display_name":"Yingda Chen","orcid":"https://orcid.org/0009-0000-7358-819X","observed_orcids":["https://orcid.org/0009-0000-7358-819X"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingda Chen","raw_affiliation_strings":["ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0000-7358-819X","affiliations":[{"raw_affiliation_string":"ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100733296","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-0043-4904","observed_orcids":["https://orcid.org/0000-0002-0043-4904"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Zhejiang University, hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-0043-4904","affiliations":[{"raw_affiliation_string":"Zhejiang University, hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5827,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.97563961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":1.0,"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":1.0,"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":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/diffusion-models","display_name":"diffusion models","score":0.7680000066757202},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.9169999957084656},{"id":"https://openalex.org/keywords/spatial-mask","display_name":"spatial mask","score":0.628000020980835},{"id":"https://openalex.org/keywords/image-inpainting","display_name":"image inpainting","score":0.7080000042915344},{"id":"https://openalex.org/keywords/diffusion-transformer","display_name":"diffusion transformer","score":0.5669999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797999978065491},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6923999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6202999949455261},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5228000283241272},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4796000123023987},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3743093.3771013","doi":"https://doi.org/10.1145/3743093.3771013","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771013","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771013","source":{"id":"https://openalex.org/S7407087938","display_name":"ACM International Conference on Multimedia in Asia (MMAsia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.01097","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.01097","pdf_url":"https://arxiv.org/pdf/2501.01097","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.01097","doi":"https://doi.org/10.48550/arxiv.2501.01097","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.01097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771013","doi":"https://doi.org/10.1145/3743093.3771013","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771013","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771013","source":{"id":"https://openalex.org/S7407087938","display_name":"ACM International Conference on Multimedia in Asia (MMAsia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2575069074","display_name":null,"funder_award_id":"62088101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073344.pdf","grobid_xml":"https://content.openalex.org/works/W4417073344.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W3081168214","https://openalex.org/W3168867926","https://openalex.org/W4200150166","https://openalex.org/W4288099666","https://openalex.org/W4312933868","https://openalex.org/W4324128075","https://openalex.org/W4385570204","https://openalex.org/W4385848774","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4387687215","https://openalex.org/W4390872297","https://openalex.org/W4390872671","https://openalex.org/W4390873054","https://openalex.org/W4392538976","https://openalex.org/W4393148714","https://openalex.org/W4393148753","https://openalex.org/W4402623742","https://openalex.org/W4402711432","https://openalex.org/W4402713111","https://openalex.org/W4402716201","https://openalex.org/W4402754201","https://openalex.org/W4403746914","https://openalex.org/W4403853618","https://openalex.org/W4404303854","https://openalex.org/W4404355664","https://openalex.org/W4405655184","https://openalex.org/W4413144849"],"related_works":["https://openalex.org/W4403791271","https://openalex.org/W7077899457","https://openalex.org/W4416380597","https://openalex.org/W4414891087","https://openalex.org/W4321854185","https://openalex.org/W4321276804","https://openalex.org/W4321649749","https://openalex.org/W3166341115","https://openalex.org/W4417267284","https://openalex.org/W4402754201"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,91],"diffusion":[3,51],"models":[4,124],"have":[5],"significantly":[6],"advanced":[7],"text-to-image":[8],"generation,":[9],"yet":[10],"global":[11],"text":[12],"prompts":[13,61],"alone":[14],"remain":[15],"insufficient":[16],"for":[17,37,50],"achieving":[18],"fine-grained":[19,72],"control":[20],"over":[21],"individual":[22],"entities":[23],"within":[24],"an":[25,101],"image.":[26],"To":[27],"address":[28],"this":[29],"limitation,":[30],"we":[31,43,78,99],"present":[32],"EliGen,":[33],"a":[34,48,68],"novel":[35],"framework":[36],"Entity-level":[38],"controlled":[39],"image":[40,96,110],"Generation.":[41],"Firstly,":[42],"put":[44],"forward":[45],"regional":[46],"attention,":[47],"mechanism":[49],"transformers":[52],"that":[53],"requires":[54],"no":[55],"additional":[56],"structures,":[57],"seamlessly":[58],"integrating":[59,119],"entity":[60],"and":[62,74,84,95,130,140],"arbitrary-shaped":[63],"spatial":[64,73,93],"masks.":[65],"By":[66],"contributing":[67],"high-quality":[69],"dataset":[70,141],"with":[71,121],"semantic":[75],"entity-level":[76,86],"annotations,":[77],"train":[79],"EliGen":[80],"to":[81,108],"achieve":[82],"robust":[83],"accurate":[85],"manipulation,":[87],"surpassing":[88],"existing":[89],"methods":[90],"both":[92],"precision":[94],"quality.":[97],"Additionally,":[98],"propose":[100],"inpainting":[102,111],"fusion":[103],"pipeline,":[104],"extending":[105],"EliGen\u2019s":[106,116],"capabilities":[107],"multi-entity":[109],"tasks.":[112],"We":[113],"further":[114],"demonstrate":[115],"flexibility":[117],"by":[118],"it":[120],"other":[122],"open-source":[123],"such":[125],"as":[126],"IP-Adapter,":[127],"In-Context":[128],"LoRA":[129],"MLLM,":[131],"unlocking":[132],"new":[133],"creative":[134],"possibilities.":[135],"The":[136],"source":[137],"code,":[138],"model,":[139],"will":[142],"be":[143],"published.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":8}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-12-06T00:00:00"}
