{"id":"https://openalex.org/W2933890497","doi":"https://doi.org/10.1109/iccv.2019.01040","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","display_name":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2933890497","doi":"https://doi.org/10.1109/iccv.2019.01040","mag":"2933890497"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2019.01040","doi":"https://doi.org/10.1109/iccv.2019.01040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.01040","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","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":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.09845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083505661","display_name":"Alaaeldin El-Nouby","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alaaeldin El-Nouby","raw_affiliation_strings":["University of Guelph","Vector Institute for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Guelph","institution_ids":["https://openalex.org/I79817857"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032287649","display_name":"Shikhar Sharma","orcid":"https://orcid.org/0000-0002-9008-2315","observed_orcids":["https://orcid.org/0000-0002-9008-2315"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shikhar Sharma","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088078468","display_name":"Hannes Schulz","orcid":"https://orcid.org/0000-0001-6408-9794","observed_orcids":["https://orcid.org/0000-0001-6408-9794"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannes Schulz","raw_affiliation_strings":["Microsoft Research","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062650781","display_name":"Devon Hjelm","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R Devon Hjelm","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049090525","display_name":"Layla El Asri","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Layla El Asri","raw_affiliation_strings":["Microsoft Research","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032466547","display_name":"Samira Ebrahimi Kahou","orcid":"https://orcid.org/0009-0005-6283-3811","observed_orcids":["https://orcid.org/0009-0005-6283-3811"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Samira Ebrahimi Kahou","raw_affiliation_strings":["Microsoft Research","McGill/Mila"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"McGill/Mila","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515","observed_orcids":["https://orcid.org/0000-0002-9322-3515"]},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Canadian Institute for Advanced Research","Montreal Institute for Learning Algorithms","University of Montreal","Mila"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canadian Institute for Advanced Research","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"Montreal Institute for Learning Algorithms","institution_ids":["https://openalex.org/I4210164802"]},{"raw_affiliation_string":"University of Montreal","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Mila","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102922725","display_name":"Graham W. Taylor","orcid":"https://orcid.org/0000-0001-5867-3652","observed_orcids":["https://orcid.org/0000-0001-5867-3652"]},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Graham Taylor","raw_affiliation_strings":["University of Guelph"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Guelph","institution_ids":["https://openalex.org/I79817857"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9306,"has_fulltext":true,"cited_by_count":101,"citation_normalized_percentile":{"value":0.96052382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10303","last_page":"10311"},"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":0.9990000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0008999999845400453,"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/object-transformation","display_name":"object transformation","score":0.7680000066757202},{"id":"https://openalex.org/keywords/background-generation","display_name":"background generation","score":0.7070000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646522521972656},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6753032207489014},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6429718732833862},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.572381317615509},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5622161626815796},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5308911204338074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4499642550945282},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33111995458602905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3274315595626831},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2669998109340668},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07009008526802063},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv.2019.01040","doi":"https://doi.org/10.1109/iccv.2019.01040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.01040","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","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":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.09845","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.09845","pdf_url":"https://arxiv.org/pdf/1811.09845","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":"mag:2933890497","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.09845v3","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1811.09845","doi":"https://doi.org/10.48550/arxiv.1811.09845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.09845","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.09845","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.09845","pdf_url":"https://arxiv.org/pdf/1811.09845","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6881384457","display_name":"Learning highly complex visual problems with deep structured models","funder_award_id":"ANR-15-CE23-0029","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2933890497.pdf","grobid_xml":"https://content.openalex.org/works/W2933890497.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2250539671","https://openalex.org/W2405756170","https://openalex.org/W2548275288","https://openalex.org/W2564591810","https://openalex.org/W2592101326","https://openalex.org/W2613404084","https://openalex.org/W2768661419","https://openalex.org/W2774015909","https://openalex.org/W2785678896","https://openalex.org/W2787579267","https://openalex.org/W2788768663","https://openalex.org/W2792263949","https://openalex.org/W2804078698","https://openalex.org/W2949117887","https://openalex.org/W2949933669","https://openalex.org/W2953064936","https://openalex.org/W2962754210","https://openalex.org/W2963966654","https://openalex.org/W2964082390","https://openalex.org/W2964121744","https://openalex.org/W2964216930","https://openalex.org/W2964286668","https://openalex.org/W3037932933","https://openalex.org/W4249013746","https://openalex.org/W4320013936","https://openalex.org/W4394668580","https://openalex.org/W6779841522"],"related_works":["https://openalex.org/W2901786679","https://openalex.org/W3093147288","https://openalex.org/W3092673631","https://openalex.org/W2894780272","https://openalex.org/W2808162831","https://openalex.org/W7117241179","https://openalex.org/W7160168470","https://openalex.org/W7163351069","https://openalex.org/W7151415103","https://openalex.org/W7165743775"],"abstract_inverted_index":{"Conditional":[0],"text-to-image":[1],"generation":[2,35,58,101],"is":[3,36,52,129,149,159],"an":[4,41,150],"active":[5],"area":[6],"of":[7,68],"research,":[8],"with":[9,72],"many":[10],"possible":[11],"applications.":[12],"Existing":[13],"research":[14],"has":[15],"primarily":[16],"focused":[17],"on":[18,45],"generating":[19],"a":[20,37,62,98],"single":[21],"image":[22,42,100],"from":[23],"available":[24,160],"conditioning":[25],"information":[26],"in":[27,89],"one":[28],"step.":[29],"One":[30],"practical":[31],"extension":[32],"beyond":[33],"one-step":[34,57],"system":[38,63],"that":[39,126],"generates":[40],"iteratively,":[43],"conditioned":[44],"ongoing":[46],"linguistic":[47],"input":[48],"or":[49],"feedback.":[50],"This":[51],"significantly":[53],"more":[54],"challenging":[55],"than":[56],"tasks,":[59],"as":[60,81,83,116,118],"such":[61],"must":[64],"understand":[65],"the":[66,75,78,84,90,108,113,133],"contents":[67],"its":[69],"generated":[70,109],"images":[71],"respect":[73],"to":[74,112,131,142],"feedback":[76,91],"history,":[77],"current":[79,114],"feedback,":[80],"well":[82,117],"interactions":[85],"among":[86],"concepts":[87],"present":[88,97],"history.":[92],"In":[93],"this":[94],"work,":[95],"we":[96],"recurrent":[99],"model":[102,128],"which":[103],"takes":[104],"into":[105],"account":[106],"both":[107],"output":[110],"up":[111],"step":[115,152],"all":[119],"past":[120],"instructions":[121],"for":[122],"generation.":[123,155],"We":[124,145],"show":[125],"our":[127,147],"able":[130],"generate":[132],"background,":[134],"add":[135],"new":[136],"objects,":[137],"and":[138,157],"apply":[139],"simple":[140],"transformations":[141],"existing":[143],"objects.":[144],"believe":[146],"approach":[148],"important":[151],"toward":[153],"interactive":[154],"Code":[156],"data":[158],"at:":[161],"https://www.microsoft.com/en-us/research/project/generative-neural-visual-artist-geneva/.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-04-11T00:00:00"}