{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:13:42Z","timestamp":1774419222662,"version":"3.50.1"},"reference-count":28,"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\/icassp49660.2025.10888420","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":1,"title":["ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillation"],"prefix":"10.1109","author":[{"given":"Ting","family":"Zhang","sequence":"first","affiliation":[{"name":"Tencent,Pattern Recognition Center, WeChat AI"}]},{"given":"Zhiqiang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tencent,Pattern Recognition Center, WeChat AI"}]},{"given":"Yeshuang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tencent,Pattern Recognition Center, WeChat AI"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent,Pattern Recognition Center, WeChat AI"}]},{"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent,Pattern Recognition Center, WeChat AI"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2575738"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2692650"},{"key":"ref3","author":"Zhou","year":"2024","journal-title":"A survey on generative ai and llm for video generation, understanding, and streaming"},{"key":"ref4","volume-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref6","first-page":"36","article-title":"Learning universal policies via text-guided video generation","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00184"},{"key":"ref8","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3728459"},{"key":"ref11","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref12","author":"Song","year":"2020","journal-title":"Score-based generative modeling through stochastic differential equations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref15","author":"Kong","year":"2021","journal-title":"On fast sampling of diffusion probabilistic models"},{"key":"ref16","author":"San-Roman","year":"2021","journal-title":"Noise estimation for generative diffusion models"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70679-1_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref20","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","article-title":"kNN-Diffusion: Image Generation via Large-Scale Retrieval","volume-title":"The Eleventh International Conference on Learning Representations","author":"Sheynin"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_3"},{"key":"ref24","author":"Dai","year":"2023","journal-title":"Emu: Enhancing image generation models using photogenic needles in a haystack"},{"key":"ref25","author":"Yan","year":"2024","journal-title":"Animated Stickers: Bringing Stickers to Life with Video Diffusion"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00654"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00211"},{"key":"ref28","author":"Yuan","year":"2024","journal-title":"VSD2M: A Large-scale Vision-language Sticker Dataset for Multi-frame Animated Sticker Generation"}],"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\/10888420.pdf?arnumber=10888420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:39Z","timestamp":1774416099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888420","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}