{"id":"https://openalex.org/W4416250818","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227241","title":"Hypergraph Prediction Diffusion Transformers for Person Image Synthesis","display_name":"Hypergraph Prediction Diffusion Transformers for Person Image Synthesis","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250818","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227241"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5102712322","display_name":"Zheng Wu","orcid":"https://orcid.org/0009-0007-5885-4999"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiheng Wu","raw_affiliation_strings":["University of Science and Technology of China,Institute of Advanced Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Institute of Advanced Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104133588","display_name":"Ningzhi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningzhi Wang","raw_affiliation_strings":["Anhui University,Institute of Artificial Intelligence,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Anhui University,Institute of Artificial Intelligence,Hefei,China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107518903","display_name":"Huilin Deng","orcid":"https://orcid.org/0009-0003-8944-1135"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huilin Deng","raw_affiliation_strings":["University of Science and Technology of China,Institute of Artificial Intelligence,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Institute of Artificial Intelligence,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066631060","display_name":"Hua Chun Zeng","orcid":"https://orcid.org/0000-0002-0215-7760"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanhui Zeng","raw_affiliation_strings":["South China University of Technology,Department of Electronic Business,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,Department of Electronic Business,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068005043","display_name":"Zhenyu Qi","orcid":"https://orcid.org/0009-0000-1108-229X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Qi","raw_affiliation_strings":["University of Science and Technology of China,Institute of Advanced Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Institute of Advanced Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089046935","display_name":"Jichen Wang","orcid":"https://orcid.org/0000-0002-4938-8283"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jichen Wang","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102712322"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37364798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.7168999910354614,"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":0.7168999910354614,"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":0.07050000131130219,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.06780000030994415,"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/hypergraph","display_name":"Hypergraph","score":0.6384000182151794},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5012999773025513},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4959999918937683},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4000999927520752},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.37770000100135803},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527000069618225},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.6384000182151794},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44830000400543213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.349700003862381},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.3077000081539154},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C2778328480","wikidata":"https://www.wikidata.org/wiki/Q1639904","display_name":"Hybrid image","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/W1901129140","https://openalex.org/W2892880750","https://openalex.org/W2963266880","https://openalex.org/W2964002510","https://openalex.org/W3034950620","https://openalex.org/W3035515747","https://openalex.org/W3096831136","https://openalex.org/W3176412779","https://openalex.org/W3180675665","https://openalex.org/W4282926996","https://openalex.org/W4312881655","https://openalex.org/W4312896571","https://openalex.org/W4312933868","https://openalex.org/W4386076520","https://openalex.org/W4390873194","https://openalex.org/W4390873332","https://openalex.org/W4402727583","https://openalex.org/W4408352797"],"related_works":[],"abstract_inverted_index":{"The":[0,72],"diffusion":[1,50,70],"model":[2,51],"has":[3,13],"emerged":[4],"as":[5],"a":[6,61,68,106],"promising":[7],"approach":[8],"for":[9,54],"image":[10,57],"generation":[11],"and":[12,67,122,144],"demonstrated":[14],"commendable":[15],"performance":[16],"in":[17,29,136,141],"Gesture-Guided":[18],"Person":[19],"Image":[20],"Synthesis":[21],"(PGPIS).":[22],"However,":[23],"existing":[24],"methods":[25,135],"face":[26],"significant":[27],"challenges":[28],"producing":[30],"high-quality":[31],"images":[32],"with":[33],"consistent":[34],"pose":[35,85],"alignment.":[36],"To":[37,97],"address":[38],"these":[39],"limitations,":[40],"we":[41,104],"propose":[42],"Hyper-PDT":[43,59,131],"(Hypergraph":[44],"Prediction":[45],"Diffusion":[46],"Transformers),":[47],"an":[48],"innovative":[49],"specifically":[52],"designed":[53],"gesture-guided":[55],"human":[56],"generation.":[58],"leverages":[60],"unique":[62],"combination":[63],"of":[64,90,101],"hypergraph":[65],"learning":[66],"transformer-based":[69],"architecture.":[71],"core":[73],"idea":[74],"is":[75],"to":[76,79],"utilize":[77],"hypergraphs":[78],"capture":[80],"high-level":[81],"feature":[82],"associations":[83],"from":[84],"images,":[86],"enabling":[87],"the":[88,94,99,126],"propagation":[89],"higher-order":[91],"information":[92],"within":[93],"semantic":[95],"space.":[96],"enhance":[98],"realism":[100],"texture":[102],"details,":[103],"introduce":[105],"dynamic":[107,118],"Classifier-Free":[108],"Guidance":[109],"mechanism,":[110],"which":[111],"adaptively":[112],"predicts":[113],"noise":[114],"during":[115],"sampling":[116],"through":[117],"scaling.":[119],"Extensive":[120],"quantitative":[121],"qualitative":[123],"evaluations":[124],"on":[125],"DeepFashion":[127],"benchmark":[128],"demonstrate":[129],"that":[130],"significantly":[132],"outperforms":[133],"state-of-the-art":[134],"PGPIS,":[137],"establishing":[138],"its":[139],"superiority":[140],"both":[142],"accuracy":[143],"visual":[145],"quality.":[146]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}