{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:22Z","timestamp":1774419982081,"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\/icassp49660.2025.10889388","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["AnimateSketches: Animate Sketches with Instance-Aware Mask"],"prefix":"10.1109","author":[{"given":"Haoge","family":"Deng","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Dai","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jijin","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonggang","family":"Qi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature13422"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201326"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592788"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566595"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00606"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00414"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022"},{"key":"ref10","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref12","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Advances in neural information processing systems","volume":"35","author":"Saharia"},{"key":"ref13","article-title":"Mod-elscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref14","article-title":"Creative sketch generation","author":"Ge","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50436-6_21"},{"key":"ref16","article-title":"Scale-adaptive diffusion model for complex sketch synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hu"},{"key":"ref17","article-title":"A neural representation of sketch drawings","author":"Ha","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5244\/c.34.159"},{"key":"ref19","article-title":"Sketchknitter: Vectorized sketch generation with diffusion models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wang"},{"key":"ref20","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Tang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417871"},{"key":"ref22","first-page":"15 869","article-title":"Diffsketcher: Text guided vector sketch synthesis through latent diffusion models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xing"},{"key":"ref23","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530068"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref26","volume-title":"Pika lab discord server"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref28","volume-title":"Runway. Gen-2: Text driven video generation","year":"2023"}],"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\/10889388.pdf?arnumber=10889388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:45Z","timestamp":1774416345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889388\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889388","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}