{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:46Z","timestamp":1777890226964,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01427","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15385-15394","source":"Crossref","is-referenced-by-count":0,"title":["Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks"],"prefix":"10.1109","author":[{"given":"Bhishma","family":"Dedhia","sequence":"first","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Bourgin","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna Kumar","family":"Singh","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Li","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Kang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhan","family":"Xu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niraj K.","family":"Jha","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","author":"Blattmann","year":"2023","journal-title":"CoRR, abs\/2311"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","article-title":"Video Generation Models as World Simulators","author":"Brooks","year":"2024","journal-title":"OpenAI Research Blog"},{"key":"ref4","volume-title":"PySceneDetect: Video Cut Detection and Analysis Tool","author":"Castellano","year":"2024"},{"key":"ref5","article-title":"PixArt- $\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","volume-title":"CoRR, abs\/2310.00426","author":"Chen","year":"2023"},{"key":"ref6","article-title":"SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction","author":"Chen","year":"2023","journal-title":"CoRR, abs\/2310"},{"key":"ref7","article-title":"AnimateAnything: FineGrained Open Domain Image Animation with Motion Guidance","author":"Dai","year":"2023","journal-title":"CoRR, abs\/2311"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref9","article-title":"Movie Gen: A Cast of Media Foundation Models","author":"Polyak","year":"2024","journal-title":"CoRR, abs\/2410"},{"key":"ref10","article-title":"Bridging the Gap to Real-World Object-Centric Learning","author":"Seitzer","year":"2023","journal-title":"CoRR, abs\/2209"},{"key":"ref11","article-title":"HunyuanVideo: A Systematic Framework for Large Video Generative Models","author":"Kong","year":"2024","journal-title":"CoRR, abs\/2412"},{"key":"ref12","article-title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","author":"Tan","year":"2024","journal-title":"CoRR, abs\/2408"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.59.103006.093629"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref15","article-title":"AnimateDiff: Animate Your Personalized Text-to- Image Diffusion Models without Specific Tuning","author":"Guo","year":"2024","journal-title":"CoRR, abs\/2307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref17","article-title":"Latent Video Diffusion Models for HighFidelity Long Video Generation","author":"He","year":"2023","journal-title":"CoRR, abs\/2211"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00245"},{"key":"ref19","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020","journal-title":"CoRR, abs\/2006.11239"},{"key":"ref20","article-title":"Video Diffusion Models","author":"Ho","year":"2022","journal-title":"CoRR, abs\/2204"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02060"},{"key":"ref22","article-title":"Scalable Adaptive Computation for Iterative Generation","author":"Jabri","year":"2023","journal-title":"CoRR, abs\/2212"},{"key":"ref23","article-title":"Thinking, Fast and Slow","author":"Kahneman","year":"2011","journal-title":"Farrar, Straus and Giroux"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0059"},{"key":"ref26","article-title":"Auto-Encoding Variational Bayes","author":"Kingma","year":"2022","journal-title":"CoRR, abs\/1312"},{"key":"ref27","article-title":"Sequence Parallelism: Long Sequence Training from System Perspective","author":"Li","year":"2022","journal-title":"CoRR, abs\/2105"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_27"},{"key":"ref30","article-title":"FreeLong: Training-Free Long Video Generation with Spectral- Blend Temporal Attention","author":"Lu","year":"2024","journal-title":"CoRR, abs\/2407"},{"key":"ref31","article-title":"Latte: Latent Diffusion Transformer for Video Generation","author":"Ma","year":"2024","journal-title":"CoRR, abs\/2401"},{"key":"ref32","article-title":"DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation","author":"Mo","year":"2023","journal-title":"CoRR, abs\/2307"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_23"},{"key":"ref34","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024","journal-title":"CoRR, abs\/2304.07193"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref36","article-title":"Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models","author":"Pernias","year":"2023","journal-title":"CoRR, abs\/2306"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref38","article-title":"FreeNoise: TuningFree Longer Video Diffusion via Noise Rescheduling","author":"Qiu","year":"2024","journal-title":"CoRR, abs\/2310"},{"key":"ref39","article-title":"Learning Transferable Visual Models from Natural Language Supervision","author":"Radford","year":"2021","journal-title":"CoRR, abs\/2103"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","article-title":"MegatronLM: Training Multi-Billion Parameter Language Models Using Model Parallelism","author":"Shoeybi","year":"2020","journal-title":"CoRR, abs\/1909.08053"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.119.1.3"},{"key":"ref44","article-title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"CoRR, abs\/1503.03585"},{"key":"ref45","volume-title":"Mochi","author":"Team","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref47","article-title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","author":"Wang","year":"2023","journal-title":"CoRR, abs\/2305"},{"key":"ref48","article-title":"ModelScope Text-to-Video Technical Report","author":"Wang","year":"2023","journal-title":"CoRR, abs\/2308"},{"key":"ref49","article-title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","volume-title":"CoRR, abs\/2306","author":"Wang","year":"2023"},{"key":"ref50","article-title":"InternVid: A Large-scale VideoText Dataset for Multimodal Understanding and Generation","author":"Wang","year":"2024","journal-title":"CoRR, abs\/2307"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref52","article-title":"Make Pixels Dance: HighDynamic Video Generation","author":"Zeng","year":"2023","journal-title":"CoRR, abs\/2311"},{"key":"ref53","article-title":"I2VGen-XL: High-Quality Image-toVideo Synthesis via Cascaded Diffusion Models","volume-title":"CoRR, abs\/2311","author":"Zhang","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"ref55","volume-title":"Open-Sora: Democratizing Efficient Video Production for All","author":"Zheng","year":"2024"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445915.pdf?arnumber=11445915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:50Z","timestamp":1777613570000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01427","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}