{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:14:13Z","timestamp":1778051653432,"version":"3.51.4"},"reference-count":117,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00061","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"547-559","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Animate Images from A Few Videos to Portray Delicate Human Actions"],"prefix":"10.1109","author":[{"given":"Haoxin","family":"Li","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingchen","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qilong","family":"Wu","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Bai","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyang","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","article-title":"Magicpose","author":"Chang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1097\/00007632-199908010-00011"},{"key":"ref7","first-page":"32","article-title":"Residual flows for invertible generative modeling","author":"Chen","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01321"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref14","article-title":"Empowering dynamics-aware text-to-video diffusion with large language models","author":"Fei","year":"2023"},{"key":"ref15","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00695"},{"key":"ref17","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref19","article-title":"Atomovideo: High fidelity image-to-video generation","author":"Gong","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref22","article-title":"Seer: Language instructed video prediction with latent diffusion models","author":"Gu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0699"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref26","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00819"},{"key":"ref28","article-title":"Animate-a-story: Storytelling with retrieval-augmented video generation","author":"He","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00245"},{"key":"ref30","first-page":"19000","article-title":"The origins and prevalence of texture bias in convolutional neural networks","author":"Hermann","year":"2020","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref32","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref35","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"ref36","first-page":"36","article-title":"Free-bloom: Zero-shot text-to-video generator with llm director and ldm animator","author":"Huang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref38","article-title":"Froster: Frozen clip is a strong teacher for open-vocabulary action recognition","author":"Huang","year":"2024"},{"key":"ref39","article-title":"Reversion: Diffusion-based relation inversion from images","author":"Huang","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00639"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730668"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref45","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref46","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680718"},{"key":"ref49","article-title":"Vstar: Generative temporal nursing for longer dynamic video synthesis","author":"Li","year":"2024"},{"key":"ref50","article-title":"Llm-grounded video diffusion models","author":"Lian","year":"2023"},{"key":"ref51","article-title":"Magicedit: High-fidelity and temporally coherent video editing","author":"Liew","year":"2023"},{"key":"ref52","article-title":"Rethinking clip-based video learners in cross-domain open-vocabulary action recognition","author":"Lin","year":"2024"},{"key":"ref53","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024"},{"key":"ref54","article-title":"Flowzero: Zero-shot text-to-video synthesis with llm-driven dynamic scene syntax","author":"Lu","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687652"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00683"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1630"},{"key":"ref60","article-title":"Customizing motion in text-to-video diffusion models","author":"Materzynska","year":"2023"},{"key":"ref61","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00861"},{"key":"ref64","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32685"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref69","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref70","article-title":"Consisti2v: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_20"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00184"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00844"},{"key":"ref78","first-page":"32","article-title":"First order motion model for image animation","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref80","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref81","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora","author":"Smith","year":"2023"},{"key":"ref82","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref83","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09396-3_9"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref88","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref89","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wang","year":"2025"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10887583"},{"key":"ref91","article-title":"Boximator: Generating rich and controllable motions for video synthesis","author":"Wang","year":"2024"},{"key":"ref92","article-title":"Videofactory: Swap attention in spatiotemporal diffusions for text-to-video generation","author":"Wang","year":"2023"},{"key":"ref93","first-page":"36","article-title":"Videocomposer: Compositional video synthesis with motion controllability","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00804"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref96","first-page":"6537","article-title":"Dreamvideo: Composing your dream videos with customized subject and motion","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wei"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref98","article-title":"Lamp: Learn a motion pattern for few-shot-based video generation","author":"Wu","year":"2023"},{"key":"ref99","article-title":"Video diffusion models are training-free motion interpreter and controller","author":"Xiao","year":"2024"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref103","article-title":"Eva: Zero-shot accurate attributes and multi-object video editing","author":"Yang","year":"2024"},{"key":"ref104","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref105","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00845"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref108","article-title":"Magicavatar: Multimodal avatar generation and animation","author":"Zhang","year":"2023"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00786"},{"key":"ref111","article-title":"Motioncrafter: One-shot motion customization of diffusion models","author":"Zhang","year":"2023"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00740"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00198"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02603"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref117","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492379.pdf?arnumber=11492379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:49Z","timestamp":1778048509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":117,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00061","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}