{"id":"https://openalex.org/W4402981454","doi":"https://doi.org/10.1109/icme57554.2024.10688056","title":"Multimedia Generative Modelling with High-Order Langevin Dynamics","display_name":"Multimedia Generative Modelling with High-Order Langevin Dynamics","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981454","doi":"https://doi.org/10.1109/icme57554.2024.10688056"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688056","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688056","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":"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/A5018232553","display_name":"Ziqiang Shi","orcid":"https://orcid.org/0000-0002-3105-6213"},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiang Shi","raw_affiliation_strings":["Fujitsu R&D Center,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu R&D Center,Beijing,China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044324493","display_name":"Rujie Liu","orcid":"https://orcid.org/0000-0002-4992-7312"},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujie Liu","raw_affiliation_strings":["Fujitsu R&D Center,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu R&D Center,Beijing,China","institution_ids":["https://openalex.org/I4210159607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19401356,"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":"6"},"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":0.9843999743461609,"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":0.9843999743461609,"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/T11309","display_name":"Music and Audio Processing","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13650","display_name":"Computational Physics and Python Applications","score":0.946399986743927,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6853747367858887},{"id":"https://openalex.org/keywords/langevin-dynamics","display_name":"Langevin dynamics","score":0.6774254441261292},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6368604898452759},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5901844501495361},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49307748675346375},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4676010012626648},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.43321162462234497},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35181719064712524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3451891243457794},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.323302686214447},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12810134887695312},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06697171926498413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6853747367858887},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.6774254441261292},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6368604898452759},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5901844501495361},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49307748675346375},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4676010012626648},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.43321162462234497},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35181719064712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3451891243457794},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.323302686214447},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12810134887695312},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06697171926498413},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688056","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688056","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Diffusion":[0],"generative":[1,24],"models":[2,59],"based":[3],"on":[4,93,119],"stochastic":[5],"differential":[6],"equations":[7],"(SDEs)":[8],"with":[9,33],"score":[10,34],"matching":[11],"have":[12],"shown":[13],"remarkable":[14],"success":[15],"in":[16,129],"data":[17,71],"generation.":[18,72],"This":[19],"paper":[20],"introduces":[21],"an":[22,74],"advanced":[23],"modeling":[25],"approach,":[26],"leveraging":[27],"high-order":[28],"Langevin":[29,41],"dynamics":[30],"(HOLD)":[31],"coupled":[32],"matching.":[35],"Our":[36],"method":[37,109],"substantiated":[38],"by":[39,85],"third-order":[40],"dynamics,":[42],"extends":[43],"traditional":[44],"SDEs":[45,52],"like":[46],"variance":[47,50],"exploding":[48],"or":[49],"preserving":[51],"for":[53],"single-variable":[54],"(data)":[55],"processes.":[56],"HOLD":[57,80],"uniquely":[58],"position,":[60],"velocity,":[61],"and":[62,68,77,101,117,121,124],"acceleration,":[63],"enhancing":[64],"both":[65],"the":[66,98],"quality":[67],"speed":[69],"of":[70,89,115],"Comprising":[73],"Ornstein-Uhlenbeck":[75],"process":[76],"two":[78,87],"Hamiltonians,":[79],"significantly":[81],"reduces":[82],"mixing":[83],"time":[84],"approximately":[86],"orders":[88],"magnitude.":[90],"Empirical":[91],"tests":[92],"unconditional":[94],"image":[95],"generation":[96],"using":[97],"public":[99],"CIFAR-10":[100,120],"ImageNet":[102,122],"datasets":[103],"demonstrate":[104],"notable":[105],"improvements.":[106],"The":[107],"proposed":[108],"achieves":[110],"state-of-the-art":[111],"Frechet":[112],"Inception":[113],"Distances":[114],"1.85":[116],"1.48":[118],"respectively,":[123],"also":[125],"showing":[126],"substantial":[127],"gains":[128],"negative":[130],"log-likelihood.":[131]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}