{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:44Z","timestamp":1777888664508,"version":"3.51.4"},"reference-count":45,"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\/iccv51701.2025.01715","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18453-18462","source":"Crossref","is-referenced-by-count":0,"title":["REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder"],"prefix":"10.1109","author":[{"given":"Yitian","family":"Zhang","sequence":"first","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Mai","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aniruddha","family":"Mahapatra","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Bourgin","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yicong","family":"Hong","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonah","family":"Casebeer","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Fu","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"An","year":"2023","journal-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation"},{"issue":"3","key":"ref2","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref3","volume-title":"Flux","year":"2024"},{"key":"ref4","author":"Caelles","year":"2019","journal-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00209"},{"key":"ref6","article-title":"Simple and controllable music generation","author":"Copet","year":"2024","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00695"},{"key":"ref10","author":"He","year":"2022","journal-title":"Latent video diffusion models for high-fidelity long video generation"},{"key":"ref11","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref13","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref14","author":"Huang","year":"2023a","journal-title":"Noise2music: Textconditioned music generation with diffusion models"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02181"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref17","volume-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref18","author":"Kreuk","year":"2022","journal-title":"Audiogen: Textually guided audio generation"},{"key":"ref19","volume-title":"Open-sora-plan","author":"Lab","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01656"},{"key":"ref21","author":"Liu","year":"2023","journal-title":"Audioldm: Text-to-audio generation with latent diffusion models"},{"key":"ref22","article-title":"Instaflow: One step is enough for high-quality diffusionbased text-to-image generation","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.10308948"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01047"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref26","author":"Meng","year":"2021","journal-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations"},{"key":"ref27","volume-title":"Sora","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","volume-title":"Runway gen-3: Next-generation video generation model","year":"2023"},{"key":"ref32","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref33","article-title":"Implicit neural representations with periodic activation functions","author":"Sitzmann","year":"2020","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref35","author":"Tang","year":"2024","journal-title":"Vidtok: A versatile and open-source video tokenizer"},{"key":"ref36","volume-title":"Kling","year":"2024"},{"key":"ref37","author":"Unterthiner","year":"2018","journal-title":"Towards accurate generative models of video: A new metric & challenges"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref40","article-title":"Omnitokenizer: A joint imagevideo tokenizer for visual generation","author":"Wang","year":"2025","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02349-y"},{"key":"ref42","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref43","author":"Yu","year":"2023","journal-title":"Language model beats diffusion-tokenizer is key to visual generation"},{"key":"ref44","article-title":"Root mean square layer normalization","author":"Zhang","year":"2019","journal-title":"NeurIPS"},{"key":"ref45","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\/11444685.pdf?arnumber=11444685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:46Z","timestamp":1777611226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01715","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}