{"id":"https://openalex.org/W4390484005","doi":"https://doi.org/10.1145/3595916.3626402","title":"DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representation","display_name":"DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representation","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390484005","doi":"https://doi.org/10.1145/3595916.3626402"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626402","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3595916.3626402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626402","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626402","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088370754","display_name":"Yuqi Leng","orcid":"https://orcid.org/0009-0005-0282-6353"},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yipeng Leng","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, China"],"raw_orcid":"https://orcid.org/0009-0005-0282-6353","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, China","institution_ids":["https://openalex.org/I2802541053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090092559","display_name":"Qiangjuan Huang","orcid":"https://orcid.org/0000-0001-6630-3467"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiangjuan Huang","raw_affiliation_strings":["Intelligent Game and Decision Lab, China"],"raw_orcid":"https://orcid.org/0000-0001-6630-3467","affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102879583","display_name":"Zhiyuan Wang","orcid":"https://orcid.org/0009-0008-7973-3624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Wang","raw_affiliation_strings":["Intelligent Game and Decision Lab, China"],"raw_orcid":"https://orcid.org/0009-0008-7973-3624","affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393301","display_name":"Yangyang Liu","orcid":"https://orcid.org/0000-0001-8941-1348"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Liu","raw_affiliation_strings":["Intelligent Game and Decision Lab, China"],"raw_orcid":"https://orcid.org/0000-0001-8941-1348","affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425880","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0000-0001-8156-5051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Intelligent Game and Decision Lab, China"],"raw_orcid":"https://orcid.org/0000-0001-8156-5051","affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088370754"],"corresponding_institution_ids":["https://openalex.org/I2802541053"],"apc_list":null,"apc_paid":null,"fwci":0.3449,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61093151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"7"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9912999868392944,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.975600004196167,"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/computer-science","display_name":"Computer science","score":0.8074615001678467},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6168616414070129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6138287782669067},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6107110381126404},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5852643251419067},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4724486470222473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4695475697517395},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4587223529815674},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45865389704704285},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4382636845111847},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3894020915031433},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.23372822999954224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074615001678467},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6168616414070129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6138287782669067},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6107110381126404},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5852643251419067},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4724486470222473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4695475697517395},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4587223529815674},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45865389704704285},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4382636845111847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3894020915031433},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.23372822999954224},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626402","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3595916.3626402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626402","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626402","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3595916.3626402","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626402","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390484005.pdf","grobid_xml":"https://content.openalex.org/works/W4390484005.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2471821491","https://openalex.org/W2753738274","https://openalex.org/W2962770929","https://openalex.org/W2963767194","https://openalex.org/W2964118024","https://openalex.org/W3034625979","https://openalex.org/W3035355202","https://openalex.org/W3036167779","https://openalex.org/W3155072588","https://openalex.org/W3162926177","https://openalex.org/W3174807077","https://openalex.org/W3176913662","https://openalex.org/W3212280254","https://openalex.org/W3217030260","https://openalex.org/W4214926101","https://openalex.org/W4226014430","https://openalex.org/W4236965008","https://openalex.org/W4281690218","https://openalex.org/W4287121833","https://openalex.org/W4312933868","https://openalex.org/W4313197389","https://openalex.org/W6779823529","https://openalex.org/W6795288823","https://openalex.org/W6796588791","https://openalex.org/W6797179183","https://openalex.org/W6838815585"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Diffusion":[0],"probabilistic":[1],"models":[2],"(DPMs)":[3],"have":[4],"shown":[5],"remarkable":[6,64],"results":[7],"on":[8,73,89,122,145],"various":[9],"image":[10,18,70,142],"synthesis":[11],"tasks":[12],"such":[13],"as":[14,85],"text-to-image":[15],"generation":[16],"and":[17,28,35,102,156,161],"inpainting.":[19],"However,":[20,79],"compared":[21,169],"to":[22,45,68,118,135,170],"other":[23],"generative":[24],"methods":[25],"like":[26],"VAEs":[27],"GANs,":[29],"DPMs":[30,50],"lack":[31],"a":[32,90,104,110],"low-dimensional,":[33],"interpretable,":[34],"well-decoupled":[36],"latent":[37,60,74,98,124,138],"code.":[38,125],"Recently,":[39],"diffusion":[40],"autoencoders":[41],"(Diff-AE)":[42],"were":[43],"proposed":[44,109,127],"explore":[46,96],"the":[47,77,97,123,137],"potential":[48],"of":[49,100],"for":[51,116,140,173],"representation":[52],"learning":[53],"via":[54,131],"autoencoding.":[55],"Diff-AE":[56,101,117],"provides":[57],"an":[58,132],"accessible":[59],"space":[61,99],"that":[62,150],"exhibits":[63],"interpretability,":[65],"allowing":[66],"us":[67],"manipulate":[69],"attributes":[71],"based":[72,144],"codes":[75,139],"from":[76],"space.":[78],"previous":[80],"works":[81],"are":[82],"not":[83],"generic":[84,105],"they":[86],"only":[87],"operated":[88],"few":[91],"limited":[92],"attributes.":[93],"To":[94],"further":[95],"achieve":[103,119],"editing":[106],"pipeline,":[107],"we":[108],"module":[111],"called":[112],"Group-supervised":[113],"AutoEncoder(dubbed":[114],"GAE)":[115],"better":[120],"disentanglement":[121],"Our":[126],"GAE":[128],"has":[129],"trained":[130],"attribute-swap":[133],"strategy":[134],"acquire":[136],"multi-attribute":[141],"manipulation":[143,155],"examples.":[146],"We":[147],"empirically":[148],"demonstrate":[149],"our":[151],"method":[152],"enables":[153],"multiple-attributes":[154],"achieves":[157],"convincing":[158],"sample":[159],"quality":[160],"attribute":[162],"alignments,":[163],"while":[164],"significantly":[165],"reducing":[166],"computational":[167],"requirements":[168],"pixel-based":[171],"approaches":[172],"representational":[174],"decoupling.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-11T08:15:01.531666","created_date":"2025-10-10T00:00:00"}