{"id":"https://openalex.org/W4283366640","doi":"https://doi.org/10.1145/3512527.3531389","title":"Disentangled Representations and Hierarchical Refinement of Multi-Granularity Features for Text-to-Image Synthesis","display_name":"Disentangled Representations and Hierarchical Refinement of Multi-Granularity Features for Text-to-Image Synthesis","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283366640","doi":"https://doi.org/10.1145/3512527.3531389"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","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/A5005938433","display_name":"Pei Dong","orcid":"https://orcid.org/0000-0001-5117-0948"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pei Dong","raw_affiliation_strings":["Shandong University, JiNan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, JiNan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068636370","display_name":"Lei Wu","orcid":"https://orcid.org/0000-0002-3872-9062"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wu","raw_affiliation_strings":["Shandong University, JiNan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, JiNan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629169","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0002-0273-5946"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Meng","raw_affiliation_strings":["Shandong University, JiNan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, JiNan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101536417","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-7290-5659"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["Shandong University, JiNan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, JiNan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005938433"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":1.0066,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76529566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"276"},"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":0.9991999864578247,"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":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9927999973297119,"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/granularity","display_name":"Granularity","score":0.9097849130630493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7801125049591064},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6766599416732788},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6691114902496338},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5881907343864441},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.527326762676239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49554431438446045},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47228437662124634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45348992943763733},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4360642731189728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3820464313030243}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.9097849130630493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801125049591064},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6766599416732788},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6691114902496338},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5881907343864441},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.527326762676239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49554431438446045},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47228437662124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45348992943763733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4360642731189728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3820464313030243},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":1,"locations":[{"id":"doi:10.1145/3512527.3531389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5400000214576721,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2183341477","https://openalex.org/W2561715562","https://openalex.org/W2903141607","https://openalex.org/W2912269676","https://openalex.org/W2913550731","https://openalex.org/W2943259397","https://openalex.org/W2962793481","https://openalex.org/W2962845008","https://openalex.org/W2963047368","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964216930","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W2982450728","https://openalex.org/W3033404132","https://openalex.org/W3033754661","https://openalex.org/W3034633089","https://openalex.org/W3035295069","https://openalex.org/W3171249923"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4382701072","https://openalex.org/W4256502920"],"abstract_inverted_index":{"In":[0],"this":[1,109],"paper,":[2],"we":[3,111,164],"focus":[4],"on":[5,213],"generating":[6],"photo-realistic":[7,123],"images":[8,124],"from":[9,38],"given":[10],"text":[11],"descriptions.":[12],"Current":[13,77],"methods":[14,30,78],"first":[15],"generate":[16,122],"an":[17],"initial":[18],"image":[19,150],"and":[20,56,101,128,161,179,193,216,222,227],"then":[21],"progressively":[22],"refine":[23,33,80],"it":[24,57,88],"to":[25,45,60,91,121,148,195,207],"a":[26,113,140,166,173,180],"high-resolution":[27],"one.":[28],"These":[29],"typically":[31],"indiscriminately":[32],"all":[34,94],"granularity":[35,48,82],"features":[36,49,68,83,103,157],"output":[37],"the":[39,43,67,74,131,136,225],"previous":[40,75],"stage.":[41,76],"However,":[42],"ability":[44],"express":[46,61,93],"different":[47,81],"in":[50,73,86,98,135],"each":[51],"stage":[52],"is":[53,58,89],"not":[54],"consistent,":[55],"difficult":[59],"precise":[62],"semantics":[63,97,134],"by":[64,125],"further":[65],"refining":[66],"with":[69],"poor":[70],"quality":[71],"generated":[72,99],"cannot":[79],"independently,":[84],"resulting":[85],"that":[87],"challenging":[90],"clearly":[92],"factors":[95,132],"of":[96,133,229],"image,":[100],"some":[102],"even":[104],"become":[105],"worse.":[106],"To":[107],"address":[108],"issue,":[110],"propose":[112],"Hierarchical":[114],"Disentangled":[115],"Representations":[116],"Generative":[117],"Adversarial":[118],"Networks":[119],"(HDR-GAN)":[120],"explicitly":[126,154],"disentangling":[127,155],"individually":[129],"modeling":[130],"image.":[137],"HDR-GAN":[138],"introduces":[139],"novel":[141,167],"component":[142],"called":[143],"multi-granularity":[144,156],"feature":[145],"disentangled":[146,189,203],"encoder":[147],"represent":[149],"information":[151],"comprehensively":[152],"through":[153],"including":[158],"pose,":[159],"shape":[160],"texture.":[162],"Moreover,":[163],"develop":[165],"Multi-granularity":[168],"Feature":[169,175,182],"Refinement":[170,176,183],"(MFR)":[171],"containing":[172],"Coarse-grained":[174],"(CFR)":[177],"model":[178],"Fine-grained":[181],"(FFR)":[184],"model.":[185],"CFR":[186],"utilizes":[187],"coarse-grained":[188],"representations":[190,204],"(e.g.,":[191,205],"pose":[192],"shape)":[194],"clarify":[196],"category":[197],"information,":[198],"while":[199],"FFR":[200],"employs":[201],"fine-grained":[202],"texture)":[206],"reflect":[208],"instance-level":[209],"details.":[210],"Extensive":[211],"experiments":[212],"two":[214],"well-studied":[215],"publicly":[217],"available":[218],"datasets":[219],"(i.e.,":[220],"CUB-200":[221],"CLEVR-SV)":[223],"demonstrate":[224],"rationality":[226],"superiority":[228],"our":[230],"method.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}