{"id":"https://openalex.org/W4385270985","doi":"https://doi.org/10.1145/3592116","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","display_name":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","publication_year":2023,"publication_date":"2023-07-26","ids":{"openalex":"https://openalex.org/W4385270985","doi":"https://doi.org/10.1145/3592116"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592116","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2301.13826","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020794872","display_name":"Hila Chefer","orcid":"https://orcid.org/0000-0003-1585-8782"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hila Chefer","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076197363","display_name":"Yuval Alaluf","orcid":"https://orcid.org/0000-0002-0076-1454"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuval Alaluf","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031567351","display_name":"Yael Vinker","orcid":"https://orcid.org/0000-0003-4402-7267"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yael Vinker","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036688260","display_name":"Daniel Cohen\u2010Or","orcid":"https://orcid.org/0000-0001-6777-7445"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Daniel Cohen-Or","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":47.684,"has_fulltext":false,"cited_by_count":179,"citation_normalized_percentile":{"value":0.999956,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"42","issue":"4","first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9956,"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":0.9956,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9812,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9647,"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-model","display_name":"Generative model","score":0.63118964},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42347968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486309},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6959755},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.63118964},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.51685697},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49332944},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4788801},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47278854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4608829},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42347968},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4163521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39832807},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20455441},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.081887215},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592116","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.13826","pdf_url":"http://arxiv.org/pdf/2301.13826","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":"http://arxiv.org/abs/2301.13826","pdf_url":"http://arxiv.org/pdf/2301.13826","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},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":17,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2963184176","https://openalex.org/W2963966654","https://openalex.org/W2965833116","https://openalex.org/W2966792645","https://openalex.org/W2987919422","https://openalex.org/W3036167779","https://openalex.org/W3174525637","https://openalex.org/W3209925571","https://openalex.org/W3216156094","https://openalex.org/W4230405732","https://openalex.org/W4286611278","https://openalex.org/W4312282373","https://openalex.org/W4312376880","https://openalex.org/W4312933868","https://openalex.org/W4312977351"],"related_works":["https://openalex.org/W4387506531","https://openalex.org/W4380551139","https://openalex.org/W4365211920","https://openalex.org/W4317695495","https://openalex.org/W4283803360","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W3014948380","https://openalex.org/W2967848559","https://openalex.org/W2280377497"],"abstract_inverted_index":{"Recent":[0],"text-to-image":[1],"generative":[2,121],"models":[3,26],"have":[4],"demonstrated":[5],"an":[6,138],"unparalleled":[7],"ability":[8],"to":[9,63,86,94,117,129,150,155,157,176,189],"generate":[10,64,177],"diverse":[11],"and":[12,51,165,192],"creative":[13],"imagery":[14],"guided":[15],"by":[16],"a":[17,203],"target":[18],"text":[19,41,163,183,206],"prompt.":[20,42,74,184],"While":[21],"revolutionary,":[22],"current":[23],"state-of-the-art":[24],"diffusion":[25],"may":[27],"still":[28],"fail":[29],"in":[30,38,79,119,161,181],"generating":[31],"images":[32],"that":[33,78,194],"fully":[34],"convey":[35],"the":[36,39,45,53,60,69,72,82,106,120,124,131,134,148,152,162,174,182,197],"semantics":[37],"given":[40],"We":[43,185],"analyze":[44],"publicly":[46],"available":[47,210],"Stable":[48],"Diffusion":[49],"model":[50,61,83,149,175],"assess":[52],"existence":[54],"of":[55,68,108,133,141,205],"catastrophic":[56],"neglect":[57],",":[58,92,113,145],"where":[59,114],"fails":[62,85],"one":[65],"or":[66,168],"more":[67,200],"subjects":[70,179],"from":[71],"input":[73],"Moreover,":[75],"we":[76,104,115,146],"find":[77],"some":[80],"cases":[81],"also":[84],"correctly":[87],"bind":[88],"attributes":[89],"(":[90],"e.g.":[91],"colors)":[93],"their":[95,171],"corresponding":[96],"subjects.":[97],"To":[98],"help":[99],"mitigate":[100],"these":[101],"failure":[102],"cases,":[103],"introduce":[105],"concept":[107],"Generative":[109],"Semantic":[110],"Nursing":[111],"(GSN)":[112],"seek":[116],"intervene":[118],"process":[122],"on":[123],"fly":[125],"during":[126],"inference":[127],"time":[128],"improve":[130],"faithfulness":[132],"generated":[135],"images.":[136],"Using":[137],"attention-based":[139],"formulation":[140],"GSN,":[142],"dubbed":[143],"Attend-and-Excite":[144],"guide":[147],"refine":[151],"cross-attention":[153],"units":[154],"attend":[156],"all":[158,178],"subject":[159],"tokens":[160],"prompt":[164],"strengthen":[166],"---":[167,170],"excite":[169],"activations,":[172],"encouraging":[173],"described":[180],"compare":[186],"our":[187,212],"approach":[188],"alternative":[190],"approaches":[191],"demonstrate":[193],"it":[195],"conveys":[196],"desired":[198],"concepts":[199],"faithfully":[201],"across":[202],"range":[204],"prompts.":[207],"Code":[208],"is":[209],"at":[211],"project":[213],"page:":[214],"https://attendandexcite.github.io/Attend-and-Excite/.":[215]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4385270985","counts_by_year":[{"year":2024,"cited_by_count":149},{"year":2023,"cited_by_count":29}],"updated_date":"2025-01-09T23:47:25.836608","created_date":"2023-07-27"}