{"id":"https://openalex.org/W7138016439","doi":"https://doi.org/10.1609/aaai.v40i14.38155","title":"VAEVQ: Enhancing Discrete Visual Tokenization Through Variational Modeling","display_name":"VAEVQ: Enhancing Discrete Visual Tokenization Through Variational Modeling","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138016439","doi":"https://doi.org/10.1609/aaai.v40i14.38155"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38155","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38155","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38155/42117","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38155/42117","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129691811","display_name":"Sicheng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sicheng Yang","raw_affiliation_strings":["Houmo AI\nXi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Houmo AI\nXi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703358","display_name":"Xing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091958","display_name":"Hanoi Open University","ror":"https://ror.org/00gjkwr85","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210091958"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Xing Hu","raw_affiliation_strings":["Houmo AI"],"affiliations":[{"raw_affiliation_string":"Houmo AI","institution_ids":["https://openalex.org/I4210091958"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689832","display_name":"Qiang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091958","display_name":"Hanoi Open University","ror":"https://ror.org/00gjkwr85","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210091958"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["Houmo AI"],"affiliations":[{"raw_affiliation_string":"Houmo AI","institution_ids":["https://openalex.org/I4210091958"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129699859","display_name":"Dawei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091958","display_name":"Hanoi Open University","ror":"https://ror.org/00gjkwr85","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210091958"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dawei Yang","raw_affiliation_strings":["Houmo AI"],"affiliations":[{"raw_affiliation_string":"Houmo AI","institution_ids":["https://openalex.org/I4210091958"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129691811"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29850746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11703","last_page":"11711"},"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":0.8015000224113464,"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":0.8015000224113464,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.04910000041127205,"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/T11448","display_name":"Face recognition and analysis","score":0.0203000009059906,"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/codebook","display_name":"Codebook","score":0.7063000202178955},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4546000063419342},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.451200008392334},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.39989998936653137},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3824999928474426},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.3675999939441681},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.3515999913215637},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.33559998869895935}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7063000202178955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5573999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5238999724388123},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.451200008392334},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3167000114917755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C153207627","wikidata":"https://www.wikidata.org/wiki/Q863873","display_name":"Code word","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38155","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38155","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38155/42117","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38155","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38155","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38155/42117","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.4888177812099457}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138016439.pdf","grobid_xml":"https://content.openalex.org/works/W7138016439.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vector":[0],"quantization":[1,90],"(VQ)":[2],"transforms":[3],"continuous":[4,42,141],"image":[5],"features":[6,119],"into":[7],"discrete":[8,44],"representations,":[9],"providing":[10],"compressed,":[11],"tokenized":[12],"inputs":[13],"for":[14,89],"generative":[15],"models.":[16],"However,":[17],"VQ-based":[18],"frameworks":[19],"suffer":[20],"from":[21],"several":[22],"issues,":[23],"such":[24],"as":[25],"non-smooth":[26],"latent":[27,97,142],"spaces,":[28],"weak":[29],"alignment":[30,113],"between":[31,40,115],"representations":[32],"before":[33],"and":[34,37,43,53,63,95,117,123,128],"after":[35],"quantization,":[36],"poor":[38],"coherence":[39],"the":[41,58,84,112,135,140],"domains.":[45],"These":[46],"issues":[47],"lead":[48],"to":[49,91,120,126,144],"unstable":[50],"codeword":[51,103],"learning":[52],"underutilized":[54],"codebooks,":[55],"ultimately":[56],"degrading":[57],"performance":[59],"of":[60],"both":[61],"reconstruction":[62],"downstream":[64],"generation":[65],"tasks.":[66],"To":[67],"this":[68],"end,":[69],"we":[70],"propose":[71],"VAEVQ,":[72],"which":[73],"comprises":[74],"three":[75],"key":[76],"components:":[77],"(1)":[78],"Variational":[79],"Latent":[80],"Quantization":[81],"(VLQ),":[82],"replacing":[83],"AE":[85],"with":[86,139],"a":[87],"VAE":[88],"leverage":[92],"its":[93],"structured":[94],"smooth":[96],"space,":[98],"thereby":[99],"facilitating":[100],"more":[101],"effective":[102],"activation;":[104],"(2)":[105],"Representation":[106],"Coherence":[107],"Strategy":[108],"(RCS),":[109],"adaptively":[110],"modulating":[111],"strength":[114],"pre-":[116],"post-quantization":[118],"enhance":[121],"consistency":[122],"prevent":[124],"overfitting":[125],"noise;":[127],"(3)":[129],"Distribution":[130],"Consistency":[131],"Regularization":[132],"(DCR),":[133],"aligning":[134],"entire":[136],"codebook":[137],"distribution":[138,143],"improve":[145],"utilization.":[146],"Extensive":[147],"experiments":[148],"on":[149],"two":[150],"benchmark":[151],"datasets":[152],"demonstrate":[153],"that":[154],"VAEVQ":[155],"outperforms":[156],"state-of-the-art":[157],"methods.":[158]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}