{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:44Z","timestamp":1774419764359,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888199","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Brick-Diffusion: Generating Long Videos with Brick-to-Wall Denoising"],"prefix":"10.1109","author":[{"given":"Yunlong","family":"Yuan","sequence":"first","affiliation":[{"name":"Fudan University,School of Data Science,China"}]},{"given":"Yuanfan","family":"Guo","sequence":"additional","affiliation":[{"name":"Huawei,Noah’s Ark Lab,China"}]},{"given":"Chunwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei,Noah’s Ark Lab,China"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei,Noah’s Ark Lab,China"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University,School of Data Science,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref2","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref3","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"ICML","author":"Nichol"},{"key":"ref6","article-title":"Cascaded Diffusion Models for High Fidelity Image Generation","author":"Ho","year":"2022","journal-title":"JMLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref8","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell"},{"key":"ref9","article-title":"PixArt-\u03b1: fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref11","article-title":"AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning","volume-title":"ICLR","author":"Guo"},{"key":"ref12","article-title":"Stable video diffusion: scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref13","article-title":"ModelScope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref14","article-title":"MagicVideo: efficient video generation with latent diffusion models","author":"Zhou","year":"2023"},{"key":"ref15","article-title":"Video diffusion models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref17","article-title":"MCVD: masked conditional video diffusion for prediction, generation, and interpolation","volume-title":"NeurIPS","author":"Voleti"},{"key":"ref18","article-title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","author":"He","year":"2023"},{"key":"ref19","article-title":"Latte: latent diffusion transformer for video generation","author":"Ma","year":"2024"},{"key":"ref20","article-title":"Make-A-Video: text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref23","article-title":"Generating long videos of dynamic scenes","volume-title":"NeurIPS","author":"Brooks"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref25","article-title":"Flexible diffusion modeling of long videos","volume-title":"NeurIPS","author":"Harvey"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.acl-long.73","article-title":"NUWA-XL: diffusion over diffusion for extremely long video generation","author":"Yin","year":"2023"},{"key":"ref27","article-title":"Phenaki: variable length video generation from open domain textual descriptions","volume-title":"ICLR","author":"Villegas"},{"key":"ref28","article-title":"SEINE: short-to-long video diffusion model for generative transition and prediction","volume-title":"ICLR","author":"Chen"},{"key":"ref29","article-title":"Gen-L-Video: multi-text to long video generation via temporal co-denoising","author":"Wang","year":"2023"},{"key":"ref30","article-title":"FreeNoise: tuning-free longer video diffusion via noise rescheduling","volume-title":"ICLR","author":"Qiu"},{"key":"ref31","article-title":"FIFO-Diffusion: generating infinite videos from text without training","author":"Kim","year":"2024"},{"key":"ref32","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song"},{"key":"ref33","article-title":"DPM-Solver: a fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"NeurIPS","author":"Lu"},{"key":"ref34","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"NeurIPS","author":"Karras"},{"key":"ref35","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"ICLR","author":"Liu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref37","article-title":"DINOv2: learning robust visual features without supervision","volume-title":"TMLR","author":"Oquab"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref39","article-title":"Aesthetic predictor","volume-title":"gitHub repository","year":"2022"},{"key":"ref40","article-title":"InternVid: a large-scale video-text dataset for multimodal understanding and generation","volume-title":"ICLR","author":"Wang"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888199.pdf?arnumber=10888199","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:31Z","timestamp":1774416271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888199\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888199","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}