{"id":"https://openalex.org/W3197494161","doi":"https://doi.org/10.1145/3461353.3461388","title":"A Survey on Multimodal Deep Learning for Image Synthesis","display_name":"A Survey on Multimodal Deep Learning for Image Synthesis","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3197494161","doi":"https://doi.org/10.1145/3461353.3461388","mag":"3197494161"},"language":"en","primary_location":{"id":"doi:10.1145/3461353.3461388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461353.3461388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461353.3461388","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3461353.3461388","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009922928","display_name":"Sanbi Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sanbi Luo","raw_affiliation_strings":["School of Cyber Security, University of Chinese Academy of Sciences, Beijing and Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing and Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009922928"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.998199999332428,"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":0.9962000250816345,"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/deep-learning","display_name":"Deep learning","score":0.9176487922668457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7661551237106323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7229472398757935},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5797982215881348},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42429691553115845},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.41619381308555603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4113519489765167}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.9176487922668457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661551237106323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7229472398757935},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5797982215881348},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42429691553115845},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.41619381308555603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4113519489765167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461353.3461388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461353.3461388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461353.3461388","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3461353.3461388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461353.3461388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461353.3461388","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197494161.pdf","grobid_xml":"https://content.openalex.org/works/W3197494161.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1580389772","https://openalex.org/W1641498739","https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W2080873731","https://openalex.org/W2117539524","https://openalex.org/W2128532956","https://openalex.org/W2133665775","https://openalex.org/W2277195237","https://openalex.org/W2326925005","https://openalex.org/W2484736472","https://openalex.org/W2533598788","https://openalex.org/W2559991484","https://openalex.org/W2619383789","https://openalex.org/W2737258237","https://openalex.org/W2747329762","https://openalex.org/W2763231886","https://openalex.org/W2767044624","https://openalex.org/W2885537606","https://openalex.org/W2885673693","https://openalex.org/W2908897581","https://openalex.org/W2914914077","https://openalex.org/W2936675519","https://openalex.org/W2953064936","https://openalex.org/W2962785568","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963413689","https://openalex.org/W2963499153","https://openalex.org/W2963502052","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2982450728","https://openalex.org/W2985076077","https://openalex.org/W2987285147","https://openalex.org/W2993158499","https://openalex.org/W2993433871","https://openalex.org/W3007486523","https://openalex.org/W3007780968","https://openalex.org/W3011628670","https://openalex.org/W3011727199","https://openalex.org/W3012404734","https://openalex.org/W3013944633","https://openalex.org/W3035564946","https://openalex.org/W3040726448","https://openalex.org/W3046359959","https://openalex.org/W3048484056","https://openalex.org/W3083475656","https://openalex.org/W3088732637","https://openalex.org/W3106759358","https://openalex.org/W3108367042","https://openalex.org/W3110969460","https://openalex.org/W3113431011","https://openalex.org/W4246464857","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4380086463","https://openalex.org/W4225161397","https://openalex.org/W3014300295","https://openalex.org/W3164822677","https://openalex.org/W2795261237"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"deep":[3,18,93,128,143,154,182],"learning":[4,129,144,155,183],"technology":[5],"has":[6,77,97],"made":[7],"breakthroughs":[8],"in":[9,30],"computer":[10],"vision.":[11],"After":[12],"using":[13],"large-scale":[14],"data":[15],"training,":[16],"the":[17,45,53,110,159,175],"neural":[19],"network":[20],"represented":[21],"by":[22],"GAN":[23],"is":[24],"significantly":[25],"better":[26],"than":[27],"previous":[28],"technologies":[29],"image":[31,89,106,130,145,156,184],"generation,":[32],"including":[33,59],"generating":[34],"more":[35,38,41],"reasonable,":[36],"higher-definition,":[37],"complex,":[39],"and":[40,51,69,82,91,115,165,177],"accurate":[42],"images.":[43],"With":[44],"continuous":[46],"development":[47],"of":[48,55,61,117,174,180],"datasets,":[49,161],"models,":[50],"applications,":[52],"fusion":[54,60],"different":[56,71],"modal":[57,72],"information,":[58,73],"natural":[62],"language,":[63],"semantic":[64],"layouts,":[65],"tags,":[66],"edge":[67],"maps,":[68],"other":[70],"to":[74,103,108,134],"generate":[75],"images":[76],"become":[78],"a":[79,100,124],"new":[80,152],"demand":[81],"challenge.":[83],"There":[84],"are":[85],"related":[86],"reviews":[87],"on":[88,126],"generation":[90,107,157],"multimodal":[92,104,127,142,153,181],"learning.":[94],"However,":[95],"there":[96],"not":[98],"been":[99],"review":[101,122],"dedicated":[102],"deep-learning":[105],"discuss":[109],"current":[111],"status,":[112],"existing":[113],"problems,":[114],"challenges":[116,176],"this":[118,121,170],"task.":[119],"Therefore,":[120],"proposes":[123],"survey":[125],"generation.":[131,146,185],"It":[132],"aims":[133],"provide":[135],"readers":[136,150],"with":[137,151],"an":[138],"application":[139],"scenario":[140],"for":[141],"Also,":[147],"it":[148],"provides":[149],"technologies,":[158],"relevant":[160],"evaluation":[162],"metrics":[163],"used,":[164],"some":[166,173],"results":[167],"comparison.":[168],"Finally,":[169],"article":[171],"describes":[172],"future":[178],"topics":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}