{"id":"https://openalex.org/W4403791271","doi":"https://doi.org/10.1145/3664647.3680898","title":"EGGen: Image Generation with Multi-entity Prior Learning through Entity Guidance","display_name":"EGGen: Image Generation with Multi-entity Prior Learning through Entity Guidance","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791271","doi":"https://doi.org/10.1145/3664647.3680898"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680898","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1885/733750735","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102387489","display_name":"Zhenhong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhenhong Sun","raw_affiliation_strings":["Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768789","display_name":"Junyan Wang","orcid":"https://orcid.org/0000-0001-5409-1292"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junyan Wang","raw_affiliation_strings":["University of Adelaide, Adelaide, SA, Australia"],"affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111532053","display_name":"Zhiyu Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Tan","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000582423","display_name":"Daoyi Dong","orcid":"https://orcid.org/0000-0002-7425-3559"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daoyi Dong","raw_affiliation_strings":["Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091591096","display_name":"Hailan Ma","orcid":"https://orcid.org/0000-0002-5039-9916"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hailan Ma","raw_affiliation_strings":["Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018243988","display_name":"Hao Li","orcid":"https://orcid.org/0000-0001-6197-0674"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101768095","display_name":"Dong Gong","orcid":"https://orcid.org/0000-0002-2668-9630"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dong Gong","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102387489"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.77,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73641265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6637","last_page":"6645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7512853145599365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5608441829681396},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5272974967956543},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43876686692237854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38020819425582886},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32801002264022827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512853145599365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608441829681396},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5272974967956543},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43876686692237854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38020819425582886},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32801002264022827}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680898","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"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733750735","is_oa":true,"landing_page_url":"https://hdl.handle.net/1885/733750735","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733750735","is_oa":true,"landing_page_url":"https://hdl.handle.net/1885/733750735","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W1861492603","https://openalex.org/W2962845008","https://openalex.org/W2963966654","https://openalex.org/W2966792645","https://openalex.org/W3165647589","https://openalex.org/W4225307095","https://openalex.org/W4281485151","https://openalex.org/W4312456860","https://openalex.org/W4312933868","https://openalex.org/W4386066731","https://openalex.org/W4386076027","https://openalex.org/W4390872387","https://openalex.org/W4390872671","https://openalex.org/W4394625750","https://openalex.org/W4402754267"],"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":{"Diffusion":[0],"models":[1,231],"have":[2],"shown":[3],"remarkable":[4],"prowess":[5],"in":[6,60,157,232],"text-to-image":[7,230],"synthesis":[8],"and":[9,28,47,72,90,176,193,215],"editing,":[10],"yet":[11],"they":[12],"often":[13,33],"stumble":[14],"when":[15],"tasked":[16],"with":[17,25,146],"interpreting":[18],"complex":[19],"prompts":[20,141,145],"that":[21,94,167,183,223],"describe":[22],"multiple":[23,45],"entities":[24,46,171],"specific":[26],"attributes":[27,71],"interrelations.":[29],"The":[30],"generated":[31],"images":[32],"contain":[34],"inconsistent":[35],"multi-entity":[36,57,153,188,235],"representation":[37],"(IMR),":[38],"reflected":[39],"as":[40],"inaccurate":[41],"presentations":[42],"of":[43,86,103,121,208],"the":[44,56,69,78,87,95,101,108,112,119,122,134,206],"their":[48,174],"attributes.":[49],"Although":[50],"providing":[51],"spatial":[52],"layout":[53],"guidance":[54,114,226],"improves":[55],"generation":[58,115,156,217,227],"quality":[59],"existing":[61,229],"works,":[62],"it":[63],"is":[64,201],"still":[65],"challenging":[66],"to":[67,107,154,172,203],"handle":[68],"leakage":[70],"avoid":[73],"unnatural":[74],"characteristics.":[75],"To":[76],"address":[77],"IMR":[79,96],"challenge,":[80],"we":[81,110,162],"first":[82],"conduct":[83],"in-depth":[84],"analyses":[85],"diffusion":[88,124,136],"process":[89,102],"attention":[91],"operation,":[92],"revealing":[93],"challenges":[97],"largely":[98],"stem":[99],"from":[100,152],"cross-attention":[104,158,165,185],"mechanisms.":[105],"According":[106],"analyses,":[109],"introduce":[111,163],"entity":[113,180,225],"mechanism,":[116],"which":[117],"maintains":[118],"integrity":[120],"original":[123],"model":[125,137],"parameters":[126],"by":[127,138],"integrating":[128],"plug-in":[129],"networks.":[130],"Our":[131,219],"work":[132],"advances":[133],"stable":[135],"segmenting":[139],"comprehensive":[140,220],"into":[142],"distinct":[143],"entity-specific":[144],"bounding":[147],"boxes,":[148],"enabling":[149],"a":[150,197],"transition":[151],"single-entity":[155],"layers.":[159],"More":[160],"importantly,":[161],"entity-centric":[164],"layers":[166,182,210],"focus":[168],"on":[169],"individual":[170],"preserve":[173],"uniqueness":[175],"accuracy,":[177],"alongside":[178],"global":[179],"alignment":[181],"refine":[184],"maps":[186],"using":[187],"priors":[189],"for":[190],"precise":[191],"positioning":[192],"attribute":[194],"accuracy.":[195],"Additionally,":[196],"linear":[198],"attenuation":[199],"module":[200],"integrated":[202],"progressively":[204],"reduce":[205],"influence":[207],"these":[209],"during":[211],"inference,":[212],"preventing":[213],"oversaturation":[214],"preserving":[216],"fidelity.":[218],"experiments":[221],"demonstrate":[222],"this":[224],"enhances":[228],"generating":[233],"detailed,":[234],"images.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}