{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:49:44Z","timestamp":1761396584839,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191565","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["ED-T2V: An Efficient Training Framework for Diffusion-based Text-to-Video Generation"],"prefix":"10.1109","author":[{"given":"Jiawei","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}]},{"given":"Weining","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,The Laboratory of Cognition and Decision Intelligence for Complex Systems"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Beijing,China"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Beijing,China"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref7","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref11","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","volume":"139","author":"Radford","year":"2021"},{"key":"ref13","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume-title":"International Conference on Machine Learning","author":"Raffel","year":"2017"},{"key":"ref14","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/iccv51070.2023.00701"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1145\/3422622"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/IJCNN48605.2020.9206665"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/IJCNN55064.2022.9891969"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1609\/aaai.v32i1.12233"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref23","article-title":"Godiva: Generating open-domain videos from natural de-scriptions","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref25","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"14 837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"Razavi","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR46437.2021.01268"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.48550\/ARXIV.1706.03762"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref31","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref33","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","volume-title":"International Conference on Learning Representations","author":"Yu","year":"2022"},{"key":"ref34","article-title":"A good image generator is what you need for high-resolution video synthesis","volume-title":"International Conference on Learning Representations","author":"Tian","year":"2021"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1007\/978-3-031-19790-1_7"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref37","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref40","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191565.pdf?arnumber=10191565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T04:06:23Z","timestamp":1710389183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191565","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}