{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:04Z","timestamp":1774420144961,"version":"3.50.1"},"reference-count":36,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887999","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Layer-Animate for Transparent Video Generation"],"prefix":"10.1109","author":[{"given":"Jingqi","family":"Bai","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Jingkai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Benzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Weihua","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref3","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref4","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref6","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref8","author":"Song","year":"2020","journal-title":"Score-based generative modeling through stochastic differential equations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"140","key":"ref14","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref15","author":"Vaswani","year":"2017","journal-title":"Attention is all you need"},{"key":"ref16","volume-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023"},{"key":"ref17","volume-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"issue":"2","key":"ref18","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref19","author":"Nichol","year":"2021","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref20","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref23","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref24","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref25","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang","year":"2024"},{"key":"ref26","author":"Gong","year":"2024","journal-title":"Atomovideo: High fidelity image-to-video generation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref28","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref30","author":"Ren","year":"2024","journal-title":"Consisti2v: Enhancing visual consistency for image-to-video generation"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00677"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3687945"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"}],"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\/10887999.pdf?arnumber=10887999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:40Z","timestamp":1774416400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887999","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}