{"id":"https://openalex.org/W4402980496","doi":"https://doi.org/10.1109/icme57554.2024.10687368","title":"Style-ACAE: Adversarial Capsule Autoencoder with Styles","display_name":"Style-ACAE: Adversarial Capsule Autoencoder with Styles","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980496","doi":"https://doi.org/10.1109/icme57554.2024.10687368"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5100735899","display_name":"Xiufeng Liu","orcid":"https://orcid.org/0000-0001-5133-6688"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiufeng Liu","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722639","display_name":"Zhong\u2010Qiu Zhao","orcid":"https://orcid.org/0000-0002-0477-4412"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqiu Zhao","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077765160","display_name":"Chen Ding","orcid":"https://orcid.org/0000-0002-1869-0076"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Ding","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.5972,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73984644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9828000068664551,"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":0.9674999713897705,"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/autoencoder","display_name":"Autoencoder","score":0.8222637176513672},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7450700998306274},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.7274054288864136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5351240634918213},{"id":"https://openalex.org/keywords/capsule","display_name":"Capsule","score":0.5077880024909973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4759238064289093},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.18722668290138245},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1371893584728241},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11284580826759338},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.09040743112564087}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8222637176513672},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7450700998306274},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7274054288864136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5351240634918213},{"id":"https://openalex.org/C2778778583","wikidata":"https://www.wikidata.org/wiki/Q147768","display_name":"Capsule","level":2,"score":0.5077880024909973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4759238064289093},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.18722668290138245},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1371893584728241},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11284580826759338},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.09040743112564087},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2766736793","https://openalex.org/W2901354392","https://openalex.org/W2962770929","https://openalex.org/W2964425131","https://openalex.org/W2989221291","https://openalex.org/W3035231706","https://openalex.org/W3043547428","https://openalex.org/W3145752657","https://openalex.org/W3174529016","https://openalex.org/W3177829265","https://openalex.org/W3180355996","https://openalex.org/W3181955432","https://openalex.org/W3217129418","https://openalex.org/W4283659112","https://openalex.org/W4312810855","https://openalex.org/W4386066464"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2502115930","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W4220775285"],"abstract_inverted_index":{"Capsule":[0,78],"networks":[1,31],"get":[2],"achievements":[3],"in":[4,10,52],"many":[5],"computer":[6],"vision":[7],"tasks.":[8],"However,":[9],"the":[11,24,44,50,68,86,104,110,131,135,139,143,168],"field":[12],"of":[13,42,49,91,127,134,142],"image":[14,147],"generation,":[15],"they":[16],"have":[17],"huge":[18],"room":[19],"for":[20,146],"improvement":[21],"compared":[22],"to":[23,102,167],"mainstream":[25],"models.":[26,171],"This":[27,137],"is":[28,138],"because":[29],"capsule":[30,63,144],"can":[32,66,159],"not":[33],"fully":[34],"parse":[35],"useful":[36],"features":[37],"and":[38,46,73,95,119,129,163],"has":[39,164],"limited":[40],"capabilities":[41],"modeling":[43],"hierarchical":[45,71],"geometrical":[47],"structure":[48,133],"object":[51,87],"background":[53],"noise.":[54],"To":[55],"tackle":[56],"these":[57],"issues,":[58],"we":[59,74,107],"propose":[60],"a":[61,89],"novel":[62,116],"autoencoder":[64],"that":[65,157],"learn":[67],"part-object":[69,128],"spatial":[70],"features,":[72],"dub":[75],"it":[76],"Adversarial":[77],"Autoencoder":[79],"with":[80],"Styles":[81],"(Style-ACAE).":[82],"Specifically,":[83],"Style-ACAE":[84,158],"decomposes":[85],"into":[88,99],"set":[90],"semantic-consistent":[92],"part-level":[93],"descriptions":[94,101],"then":[96],"assembles":[97],"them":[98],"object-level":[100],"build":[103],"hierarchy.":[105],"Furthermore,":[106],"effectively":[108],"apply":[109],"modified":[111],"generator":[112,123],"structure,":[113],"which":[114],"introduces":[115],"style":[117],"modulation":[118],"demodulation.":[120],"The":[121,153],"new":[122],"handles":[124],"long-range":[125],"dependency":[126],"captures":[130],"global":[132],"object.":[136],"first":[140],"case":[141],"network":[145],"generation":[148],"on":[149],"commonly":[150],"used":[151],"benchmarks.":[152],"experimental":[154],"results":[155],"show":[156],"generate":[160],"high-quality":[161],"images":[162],"competitive":[165],"performance":[166],"state-of-the-art":[169],"generative":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}