{"id":"https://openalex.org/W4393148753","doi":"https://doi.org/10.1609/aaai.v38i5.28204","title":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance","display_name":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393148753","doi":"https://doi.org/10.1609/aaai.v38i5.28204"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28204","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28204/28404","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28204/28404","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085018165","display_name":"Wan-Duo Kurt","orcid":"https://orcid.org/0000-0002-9499-2623"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Wan-Duo Kurt Ma","raw_affiliation_strings":["Victoria University of Wellington"],"affiliations":[{"raw_affiliation_string":"Victoria University of Wellington","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082039339","display_name":"Avisek Lahiri","orcid":"https://orcid.org/0000-0002-9783-4073"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avisek Lahiri","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109995915","display_name":"Jonathan Lewis","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"J. P. Lewis","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037660468","display_name":"Thomas Leung","orcid":"https://orcid.org/0000-0001-8193-0709"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Leung","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087492771","display_name":"W. Bastiaan Kleijn","orcid":"https://orcid.org/0000-0002-1973-3920"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["NZ","US"],"is_corresponding":false,"raw_author_name":"W. Bastiaan Kleijn","raw_affiliation_strings":["Victoria University of Wellington\nGoogle Research"],"affiliations":[{"raw_affiliation_string":"Victoria University of Wellington\nGoogle Research","institution_ids":["https://openalex.org/I41156924","https://openalex.org/I1291425158"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":36.422,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":15,"citation_normalized_percentile":{"value":0.992424,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"38","issue":"5","first_page":"4098","last_page":"4106"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.7381,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.7381,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.709,"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":[],"concepts":[{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.56554407},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5487443},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5134972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47293547},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4124599},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38744295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38425982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3605959},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13215917},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28204","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28204/28404","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2302.13153","pdf_url":"https://arxiv.org/pdf/2302.13153","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28204","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28204/28404","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":29,"referenced_works":["https://openalex.org/W1518553298","https://openalex.org/W1959608418","https://openalex.org/W2129069237","https://openalex.org/W2959300817","https://openalex.org/W3004970274","https://openalex.org/W3036167779","https://openalex.org/W3121370741","https://openalex.org/W3153469116","https://openalex.org/W3166396011","https://openalex.org/W4214926101","https://openalex.org/W4224035735","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4287029626","https://openalex.org/W4288099666","https://openalex.org/W4289785095","https://openalex.org/W4307785224","https://openalex.org/W4310628982","https://openalex.org/W4311252447","https://openalex.org/W4312824283","https://openalex.org/W4312933868","https://openalex.org/W4313484371","https://openalex.org/W4320831569","https://openalex.org/W4321276804","https://openalex.org/W4322716710","https://openalex.org/W4385004666","https://openalex.org/W4385271281","https://openalex.org/W4386075631","https://openalex.org/W4386076027"],"related_works":["https://openalex.org/W2979526210","https://openalex.org/W2160609742","https://openalex.org/W2141691317","https://openalex.org/W2110846987","https://openalex.org/W2049254832","https://openalex.org/W2031091109","https://openalex.org/W1997414638","https://openalex.org/W1983548084","https://openalex.org/W1982160337","https://openalex.org/W1971380437"],"abstract_inverted_index":{"Text-guided":[0],"diffusion":[1,152],"models":[2,43,153],"such":[3,53],"as":[4,54,80,162],"DALLE-2,":[5],"Imagen,":[6],"and":[7,69,73,87,183,192],"Stable":[8],"Diffusion":[9,166],"are":[10,36],"able":[11],"to":[12,46,63,99,157,202],"generate":[13],"an":[14,127,179],"effectively":[15],"endless":[16],"variety":[17],"of":[18,37,67,119,150,159,178],"images":[19,35,75,156],"given":[20],"only":[21,198],"a":[22,95,144,185,199],"short":[23],"text":[24],"prompt":[25,113],"describing":[26],"the":[27,34,65,83,101,106,109,116,148,189,193],"desired":[28,134],"image":[29],"content.":[30],"In":[31,90],"many":[32],"cases":[33],"very":[38],"high":[39],"quality.":[40],"However,":[41],"these":[42,137],"often":[44],"struggle":[45],"compose":[47],"scenes":[48],"containing":[49],"several":[50],"key":[51],"objects":[52,70,120,191],"characters":[55,68],"in":[56,78,82,136,163],"specified":[57],"positional":[58,170],"relationships.":[59],"The":[60,140],"missing":[61],"capability":[62],"``direct''":[64],"placement":[66],"both":[71],"within":[72],"across":[74],"is":[76,143],"crucial":[77],"storytelling,":[79],"recognized":[81],"literature":[84],"on":[85,105],"film":[86],"animation":[88],"theory.":[89],"this":[91],"work,":[92],"we":[93,125],"take":[94],"particularly":[96],"straightforward":[97],"approach":[98,142],"providing":[100],"needed":[102],"direction.":[103],"Drawing":[104],"observation":[107],"that":[108,130],"cross-attention":[110,138],"maps":[111],"for":[112],"words":[114],"reflect":[115],"spatial":[117],"layout":[118],"denoted":[121],"by":[122],"those":[123],"words,":[124],"introduce":[126],"optimization":[128],"objective":[129],"produces":[131],"``activation''":[132],"at":[133],"positions":[135],"maps.":[139],"resulting":[141],"step":[145],"toward":[146],"generalizing":[147],"applicability":[149],"text-guided":[151],"beyond":[154],"single":[155],"collections":[158],"related":[160],"images,":[161],"storybooks.":[164],"Directed":[165],"provides":[167],"easy":[168],"high-level":[169],"control":[171],"over":[172],"multiple":[173],"objects,":[174],"while":[175],"making":[176],"use":[177],"existing":[180],"pre-trained":[181],"model":[182],"maintaining":[184],"coherent":[186],"blend":[187],"between":[188],"positioned":[190],"background.":[194],"Moreover,":[195],"it":[196],"requires":[197],"few":[200],"lines":[201],"implement.":[203]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4393148753","counts_by_year":[{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":3}],"updated_date":"2025-01-04T06:02:54.178966","created_date":"2024-03-26"}