{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:35:43Z","timestamp":1774938943541,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004787","name":"Hong Kong Research Grants Council","doi-asserted-by":"publisher","award":["GRF-15229423"],"award-info":[{"award-number":["GRF-15229423"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3672374","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:17:43Z","timestamp":1773692263000},"page":"3324-3338","source":"Crossref","is-referenced-by-count":0,"title":["MotionPrior: Exploring Efficient Learning of Motion Concepts for Few-Shot Video Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2784-6738","authenticated-orcid":false,"given":"Yaosi","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Chang Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref2","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref3","first-page":"29020","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Villegas"},{"key":"ref4","first-page":"7594","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Wang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref7","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023","journal-title":"arXiv:2304.08477"},{"key":"ref8","article-title":"ModelScope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv:2308.06571"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref11","first-page":"7657","article-title":"Ground-A-video: Zero-shot grounded video editing using text-to-image diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jeong"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02121"},{"key":"ref13","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023","journal-title":"arXiv:2303.17599"},{"key":"ref14","article-title":"Video-P2P: Video editing with cross-attention control","author":"Liu","year":"2023","journal-title":"arXiv:2303.04761"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00677"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3003227"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123549"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086082"},{"key":"ref20","first-page":"24932","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01029"},{"key":"ref22","first-page":"30133","article-title":"Make-A-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Singer"},{"key":"ref23","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv:2211.13221"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref25","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv:2310.19512"},{"key":"ref26","article-title":"Swap attention in spatiotemporal diffusions for text-to-video generation","author":"Wang","year":"2023","journal-title":"arXiv:2305.10874"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612707"},{"key":"ref28","article-title":"LAVIE: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2023","journal-title":"arXiv:2309.15103"},{"key":"ref29","first-page":"3384","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref30","article-title":"Control-A-video: Controllable text-to-video diffusion models with motion prior and reward feedback learning","author":"Chen","year":"2023","journal-title":"arXiv:2305.13840"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_27"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00804"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref36","article-title":"I2V-adapter: A general image-to-video adapter for diffusion models","author":"Guo","year":"2023","journal-title":"arXiv:2312.16693"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00414"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01965"},{"key":"ref39","first-page":"1069","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gal"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref43","article-title":"DreamVideo: Composing your dream videos with customized subject and motion","author":"Wei","year":"2023","journal-title":"arXiv:2312.04433"},{"key":"ref44","article-title":"VideoBooth: Diffusion-based video generation with image prompts","author":"Jiang","year":"2023","journal-title":"arXiv:2312.00777"},{"key":"ref45","article-title":"CustomVideo: Customizing text-to-video generation with multiple subjects","author":"Wang","year":"2024","journal-title":"arXiv:2401.09962"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01462"},{"key":"ref48","first-page":"8826","article-title":"FLATTEN: Optical FLow-guided ATTENtion for consistent text-to-video editing","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Cong"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref51","article-title":"NewMove: Customizing text-to-video models with novel motions","author":"Materzynska","year":"2023","journal-title":"arXiv:2312.04966"},{"key":"ref52","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref53","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref54","first-page":"240","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref56","first-page":"14205","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref57","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref59","first-page":"22275","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Podell"},{"key":"ref60","first-page":"1","article-title":"The MUG facial expression database","volume-title":"Proc. 11th Int. Workshop Image Anal. Multimedia Interact. Services","author":"Aifanti"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00861"},{"key":"ref64","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref66","article-title":"I2 VGen-XL: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv:2311.04145"},{"key":"ref67","volume-title":"Gen-2","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11435273.pdf?arnumber=11435273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:07:59Z","timestamp":1774933679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11435273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3672374","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}