{"id":"https://openalex.org/W7160298297","doi":"https://doi.org/10.1109/wacv61042.2026.00206","title":"Pyramidal Spectrum: Frequency-based Hierarchically Vector Quantized VAE for Videos","display_name":"Pyramidal Spectrum: Frequency-based Hierarchically Vector Quantized VAE for Videos","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160298297","doi":"https://doi.org/10.1109/wacv61042.2026.00206"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5135380155","display_name":"Tushar Prakash","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tushar Prakash","raw_affiliation_strings":["Independent Researcher,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135343806","display_name":"Onkar Susladkar","orcid":null},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Onkar Susladkar","raw_affiliation_strings":["UIUC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Inderjit S. Dhillon","raw_affiliation_strings":["UT Austin and Google Research,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin and Google Research,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012290807","display_name":"Sparsh Mittal","orcid":"https://orcid.org/0000-0002-2908-993X"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sparsh Mittal","raw_affiliation_strings":["IIT Roorkee,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Roorkee,India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52100032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2073","last_page":"2082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.2353000044822693,"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"}},"topics":[{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.2353000044822693,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.19850000739097595,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.09610000252723694,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3634999990463257},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2913999855518341},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27250000834465027},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.2578999996185303}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5464000105857849},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5249000191688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5188999772071838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3287999927997589},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29440000653266907},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1996021349","https://openalex.org/W2123119012","https://openalex.org/W2146395539","https://openalex.org/W2511458122","https://openalex.org/W2526050071","https://openalex.org/W3180355996","https://openalex.org/W3202918664","https://openalex.org/W3204588463","https://openalex.org/W4249722514","https://openalex.org/W4312633146","https://openalex.org/W4312933868","https://openalex.org/W4312974539","https://openalex.org/W4313147094","https://openalex.org/W4313156423","https://openalex.org/W4386076280","https://openalex.org/W4403716358","https://openalex.org/W4413145445","https://openalex.org/W4415708364","https://openalex.org/W4415798714","https://openalex.org/W7160038167","https://openalex.org/W7160168013"],"related_works":[],"abstract_inverted_index":{"Variational":[0,83],"Autoencoders":[1],"(VAEs)":[2],"form":[3],"the":[4],"foundation":[5],"of":[6,49,65,171],"modern":[7],"video":[8,71],"generation":[9],"models.":[10],"In":[11],"particular,":[12],"discrete":[13,40],"latent":[14],"VAEs":[15,41],"with":[16,156],"vector":[17],"quantization":[18,60,115],"have":[19],"gained":[20],"prominence":[21],"for":[22,70,86],"their":[23],"superior":[24],"perceptual":[25,158],"sharpness,":[26],"ability":[27],"to":[28,35,52,98,123,162],"model":[29],"long-range":[30],"dynamics,":[31],"and":[32,57,94,102,152,165],"efficient":[33],"adaptation":[34],"downstream":[36],"tasks.":[37],"However,":[38],"existing":[39],"face":[42],"two":[43],"key":[44],"limitations:":[45],"(i)":[46],"a":[47,79,113,134,140],"lack":[48],"frequency-domain":[50],"modeling":[51,64],"enhance":[53],"global":[54,100],"spatiotemporal":[55,67],"understanding,":[56],"(ii)":[58],"fixed-resolution":[59],"schemes,":[61],"preventing":[62],"effective":[63],"coarse-to-fine":[66],"hierarchies":[68],"essential":[69],"generation.":[72],"To":[73,128],"address":[74],"these":[75],"limitations,":[76],"we":[77,132],"propose":[78],"Pyramidal":[80,109],"Vector":[81,110],"Quantized":[82],"Autoencoder":[84],"(PVQ-VAE)":[85],"videos.":[87],"PVQ-VAE\u2019s":[88],"encoder\u2013decoder":[89],"leverages":[90],"Fast":[91],"Fourier":[92],"Transform":[93,97],"Discrete":[95],"Wavelet":[96],"capture":[99,125],"semantics":[101],"multi-scale":[103,126],"local":[104],"details":[105],"jointly.":[106],"We":[107],"introduce":[108,133],"Quantization":[111],"(PVQ),":[112],"hierarchical":[114],"scheme":[116],"that":[117],"discretizes":[118],"features":[119],"at":[120,160],"multiple":[121],"resolutions":[122],"better":[124],"information.":[127],"further":[129],"boost":[130],"fidelity,":[131],"cross-modal":[135],"contrastive":[136],"loss":[137],"guided":[138],"by":[139],"pretrained":[141],"high-resolution":[142],"image":[143],"VAE.":[144],"PVQ-VAE":[145],"achieves":[146],"state-of-the-art":[147],"performance":[148],"on":[149],"WebVid-val,":[150],"COCO-val,":[151],"MCL-JCV,":[153],"reconstructing":[154],"videos":[155],"high":[157],"quality":[159],"up":[161],"32\u00d7":[163],"spatial":[164],"16\u00d7":[166],"temporal":[167],"compression.":[168],"Project":[169],"page":[170],"PVQ-VAE.":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}