{"id":"https://openalex.org/W3092775865","doi":"https://doi.org/10.1145/3394171.3413505","title":"Describe What to Change","display_name":"Describe What to Change","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092775865","doi":"https://doi.org/10.1145/3394171.3413505","mag":"3092775865"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100375513","display_name":"Yahui Liu","orcid":"https://orcid.org/0000-0003-4398-8867"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yahui Liu","raw_affiliation_strings":["University of Trento &amp; FBK, Trento, Italy","University of Trento [Trento]","Fondazione Bruno Kessler [Trento, Italy]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento &amp; FBK, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"University of Trento [Trento]","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Fondazione Bruno Kessler [Trento, Italy]","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081236916","display_name":"Marco De Nadai","orcid":"https://orcid.org/0000-0001-8466-3933"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco De Nadai","raw_affiliation_strings":["FBK, Trento, Italy","Fondazione Bruno Kessler [Trento, Italy]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FBK, Trento, Italy","institution_ids":[]},{"raw_affiliation_string":"Fondazione Bruno Kessler [Trento, Italy]","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061528283","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0003-3444-8383"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China","The Chinese University of Hong Kong [Hong Kong]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong [Hong Kong]","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101425369","display_name":"Huayang Li","orcid":"https://orcid.org/0000-0003-3539-8648"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huayang Li","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China","Tencent [Shenzhen]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent [Shenzhen]","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I4210124484","display_name":"Directorate-General for Interpretation","ror":"https://ror.org/03728bb41","country_code":"BE","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210124484"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["BE","FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["Inria Grenoble, Grenoble, France","Interpretation and Modelling of Images and Videos"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble, Grenoble, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Interpretation and Modelling of Images and Videos","institution_ids":["https://openalex.org/I4210124484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["University of Trento &amp; Huawei Ireland, Trento, Italy","University of Trento [Trento]","Huawei Research Ireland [Dublin]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento &amp; Huawei Ireland, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"University of Trento [Trento]","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Huawei Research Ireland [Dublin]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048877432","display_name":"Bruno Lepri","orcid":"https://orcid.org/0000-0003-1275-2333"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Bruno Lepri","raw_affiliation_strings":["FBK, Trento, Italy","Fondazione Bruno Kessler [Trento, Italy]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FBK, Trento, Italy","institution_ids":[]},{"raw_affiliation_string":"Fondazione Bruno Kessler [Trento, Italy]","institution_ids":["https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1357","last_page":"1365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9936000108718872,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9921000003814697,"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/closed-captioning","display_name":"Closed captioning","score":0.840080976486206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7930679321289062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6176376342773438},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6042406558990479},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6023905277252197},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6017398238182068},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5999704599380493},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5363600850105286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4798421561717987},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4628990888595581},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.45393621921539307},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4325951635837555},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42382198572158813},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.41452592611312866},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3220354914665222}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.840080976486206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930679321289062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176376342773438},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6042406558990479},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6023905277252197},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6017398238182068},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5999704599380493},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5363600850105286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4798421561717987},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4628990888595581},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.45393621921539307},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4325951635837555},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42382198572158813},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.41452592611312866},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3220354914665222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3394171.3413505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02930687v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02930687","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"28th ACM International Conference on Multimedia, MM'20, Oct 2020, Seatle, United States. pp.1357-1365, &#x27E8;10.1145/3394171.3413505&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unitn.it:11572/284442","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/284442","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2125389028","https://openalex.org/W2183341477","https://openalex.org/W2493916176","https://openalex.org/W2552161745","https://openalex.org/W2603777577","https://openalex.org/W2626778328","https://openalex.org/W2739748921","https://openalex.org/W2807033398","https://openalex.org/W2883861033","https://openalex.org/W2897946384","https://openalex.org/W2904407897","https://openalex.org/W2916279611","https://openalex.org/W2950404765","https://openalex.org/W2957167378","https://openalex.org/W2960274051","https://openalex.org/W2961363059","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W2962845008","https://openalex.org/W2963047368","https://openalex.org/W2963073614","https://openalex.org/W2963145877","https://openalex.org/W2963163163","https://openalex.org/W2963177331","https://openalex.org/W2963255313","https://openalex.org/W2963306805","https://openalex.org/W2963373786","https://openalex.org/W2963420272","https://openalex.org/W2963890275","https://openalex.org/W2963981733","https://openalex.org/W2964270502","https://openalex.org/W2978052557","https://openalex.org/W2987068815","https://openalex.org/W2991466165","https://openalex.org/W2993158499","https://openalex.org/W3034600949","https://openalex.org/W3122887115"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W3009270862","https://openalex.org/W1516679419","https://openalex.org/W190396239"],"abstract_inverted_index":{"Manipulating":[0],"visual":[1,143,234],"attributes":[2,85,121],"of":[3,27,43,58,86,118,122,182,194,226],"images":[4],"through":[5,90],"human-written":[6],"text":[7,170],"is":[8],"a":[9,74,87,91,111,115,158],"very":[10],"challenging":[11],"task.":[12],"On":[13,31],"the":[14,21,24,28,32,40,51,56,59,84,97,120,123,138,142,150,153,162,165,195,201,221],"one":[15],"hand,":[16,34],"models":[17,35],"have":[18,36,130],"to":[19,37,53,63,100,103,131,148,179,223],"learn":[20],"manipulation":[22],"without":[23],"ground":[25],"truth":[26],"desired":[29,60,124],"output.":[30],"other":[33],"deal":[38],"with":[39,233],"inherent":[41],"ambiguity":[42],"natural":[44],"language.":[45],"Previous":[46],"research":[47,227],"usually":[48],"requires":[49],"either":[50],"user":[52],"describe":[54],"all":[55,119],"characteristics":[57],"image":[61,66,89,139,160],"or":[62],"use":[64],"richly-annotated":[65],"captioning":[67],"datasets.":[68],"In":[69],"this":[70],"work,":[71],"we":[72],"propose":[73],"novel":[75],"unsupervised":[76],"approach,":[77],"based":[78],"on":[79,207],"image-to-image":[80],"translation,":[81],"that":[82,129,200],"alters":[83],"given":[88],"command-like":[92],"sentence":[93],"such":[94],"as":[95],"\"change":[96],"hair":[98,176],"color":[99],"black\".":[101],"Contrarily":[102],"state-of-the-art":[104],"approaches,":[105],"our":[106,188,217],"model":[107,136,203],"does":[108],"not":[109],"require":[110],"human-annotated":[112],"dataset":[113],"nor":[114],"textual":[116,154,229],"description":[117],"image,":[125],"but":[126],"only":[127],"those":[128],"be":[132,172],"modified.":[133],"Our":[134],"proposed":[135,202],"disentangles":[137],"content":[140,163],"from":[141,161],"attributes,":[144],"and":[145,164,213,230],"it":[146],"learns":[147],"modify":[149],"latter":[151],"using":[152],"description,":[155],"before":[156],"generating":[157],"new":[159,224],"modified":[166],"attribute":[167],"representation.":[168],"Because":[169],"might":[171],"inherently":[173],"ambiguous":[174],"(blond":[175],"may":[177],"refer":[178],"different":[180],"shadows":[181],"blond,":[183],"e.g.":[184],"golden,":[185],"icy,":[186],"sandy),":[187],"method":[189],"generates":[190],"multiple":[191],"stochastic":[192],"versions":[193],"same":[196],"translation.":[197],"Experiments":[198],"show":[199],"achieves":[204],"promising":[205],"performances":[206],"two":[208],"large-scale":[209],"public":[210],"datasets:":[211],"CelebA":[212],"CUB.":[214],"We":[215],"believe":[216],"approach":[218],"will":[219],"pave":[220],"way":[222],"avenues":[225],"combining":[228],"speech":[231],"commands":[232],"attributes.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":14}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2020-10-22T00:00:00"}
