{"id":"https://openalex.org/W4402917123","doi":"https://doi.org/10.1109/icip51287.2024.10647765","title":"Adaptively Hierarchical Quantization Variational Autoencoder Based on Feature Decoupling and Semantic Consistency for Image Generation","display_name":"Adaptively Hierarchical Quantization Variational Autoencoder Based on Feature Decoupling and Semantic Consistency for Image Generation","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402917123","doi":"https://doi.org/10.1109/icip51287.2024.10647765"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647765","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647765","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 Image Processing (ICIP)","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/A5100386002","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0001-5336-5431"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Samsung R&D Institute China,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China,Beijing","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028327919","display_name":"Hyunhee Park","orcid":"https://orcid.org/0000-0003-3810-7367"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunhee Park","raw_affiliation_strings":["Samsung Electronics,Department of Camera Innovation Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Department of Camera Innovation Group","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059749048","display_name":"Hanchao Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanchao Jia","raw_affiliation_strings":["Samsung R&D Institute China,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China,Beijing","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380519","display_name":"Fan Wang","orcid":"https://orcid.org/0000-0002-4392-7821"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Wang","raw_affiliation_strings":["Samsung R&D Institute China,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China,Beijing","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049156680","display_name":"Jianxing Zhang","orcid":"https://orcid.org/0000-0003-4091-2189"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxing Zhang","raw_affiliation_strings":["Samsung R&D Institute China,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China,Beijing","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026945887","display_name":"Xiangyu Kong","orcid":"https://orcid.org/0000-0002-7765-2643"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Kong","raw_affiliation_strings":["Samsung R&D Institute China,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China,Beijing","institution_ids":["https://openalex.org/I4210155230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"2417","last_page":"2423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9239000082015991,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9239000082015991,"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":0.9229000210762024,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.902899980545044,"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":0.8342666625976562},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.6946021318435669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6082834601402283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6034117937088013},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.600821852684021},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5025343894958496},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47378870844841003},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47280827164649963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3569335639476776},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3332459330558777},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12038755416870117},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07191285490989685},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.06439915299415588}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8342666625976562},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6946021318435669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6082834601402283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6034117937088013},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.600821852684021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5025343894958496},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47378870844841003},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47280827164649963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3569335639476776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3332459330558777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12038755416870117},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07191285490989685},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.06439915299415588},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647765","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647765","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 Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2752796333","https://openalex.org/W2889680312","https://openalex.org/W2922386270","https://openalex.org/W3012002796","https://openalex.org/W3090052686","https://openalex.org/W3166762869","https://openalex.org/W3180355996","https://openalex.org/W4307105111","https://openalex.org/W4312974539","https://openalex.org/W6718379498","https://openalex.org/W6729448088","https://openalex.org/W6757146666","https://openalex.org/W6762931180","https://openalex.org/W6765779288","https://openalex.org/W6780593937","https://openalex.org/W6842542927","https://openalex.org/W6991418308"],"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/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2909431601"],"abstract_inverted_index":{"The":[0],"Vector":[1],"Quantized":[2],"Variational":[3,51],"AutoEncoder":[4,52],"(VQ-VAE)":[5],"has":[6],"shown":[7],"great":[8],"potential":[9],"in":[10,39],"image":[11],"generation,":[12],"especially":[13],"the":[14,20,47,64,72,81,94,101,108,119,125],"methods":[15],"with":[16,58,113,137],"hierarchical":[17,28,82],"features.":[18],"However,":[19],"lack":[21],"of":[22,24,67,96],"decoupling":[23,85],"structural":[25,36,87],"information":[26,88],"between":[27],"features":[29],"leads":[30],"to":[31,54,79,106,124],"semantic":[32,65],"inconsistencies":[33],"and":[34,89],"redundant":[35],"features,":[37,83],"resulting":[38],"incompatible":[40],"outputs.":[41],"In":[42],"this":[43],"study,":[44],"we":[45,70,99],"propose":[46],"Adaptively":[48],"Hierarchical":[49],"Quantization":[50],"(AHQ-VAE)":[53],"generate":[55,107,134],"high-fidelity":[56],"images":[57,136],"a":[59,138],"unified":[60,139],"structure.":[61,140],"To":[62,92],"ensure":[63,93],"consistency":[66,95],"continuous":[68],"space,":[69,98],"employ":[71],"Spatially":[73],"Consistent":[74],"Semantic":[75],"Embedding":[76],"(SCSE)":[77],"module":[78],"align":[80],"while":[84],"global":[86,126],"local":[90,120],"details.":[91],"discrete":[97],"introduce":[100],"Adaptive":[102],"Bottom":[103],"Quantizer":[104],"(ABQ)":[105],"quantized":[109,114],"bottom":[110],"codes":[111],"consistent":[112],"top":[115],"codes,":[116],"so":[117],"that":[118],"details":[121],"can":[122,133],"adapt":[123],"semantics.":[127],"Extensive":[128],"experiments":[129],"demonstrate":[130],"our":[131],"approach":[132],"high-quality":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}