{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:44Z","timestamp":1778048504492,"version":"3.51.4"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00206","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2073-2082","source":"Crossref","is-referenced-by-count":0,"title":["Pyramidal Spectrum: Frequency-based Hierarchically Vector Quantized VAE for Videos"],"prefix":"10.1109","author":[{"given":"Tushar","family":"Prakash","sequence":"first","affiliation":[{"name":"Independent Researcher,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onkar","family":"Susladkar","sequence":"additional","affiliation":[{"name":"UIUC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inderjit S.","family":"Dhillon","sequence":"additional","affiliation":[{"name":"UT Austin and Google Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sparsh","family":"Mittal","sequence":"additional","affiliation":[{"name":"IIT Roorkee,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","volume-title":"Proceedings of ICML workshop on unsupervised and transfer learning","author":"Baldi"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11210036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01456"},{"key":"ref7","first-page":"4479","article-title":"Fast fourier convolution","volume":"33","author":"Chi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/18.57199"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(90)90158-U"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref15","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref16","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref17","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01656"},{"key":"ref20","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"Nov","key":"ref22","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref23","article-title":"Openvid-1m: A large-scale high-quality dataset for text-to-video generation","author":"Nan","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00350"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref28","article-title":"Motionaura: Generating high-quality and motion consistent videos using discrete diffusion","author":"Susladkar","year":"2024"},{"key":"ref29","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref31","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021"},{"key":"ref32","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref33","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref35","article-title":"Language model beats diffusion\u2013tokenizer is key to visual generation","author":"Yu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17989-2_3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01446"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0409"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491992.pdf?arnumber=11491992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:08:48Z","timestamp":1778047728000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00206","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}