{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T21:04:59Z","timestamp":1784322299300,"version":"3.55.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3449075","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T17:50:02Z","timestamp":1724435402000},"page":"10829-10844","source":"Crossref","is-referenced-by-count":41,"title":["LIA: Latent Image Animator"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9487-6187","authenticated-orcid":false,"given":"Yaohui","family":"Wang","sequence":"first","affiliation":[{"name":"Inria Center at Université Côte d'Azur, 2004 Rte des Lucioles, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8124-532X","authenticated-orcid":false,"given":"Di","family":"Yang","sequence":"additional","affiliation":[{"name":"Inria Center at Université Côte d'Azur, 2004 Rte des Lucioles, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2988-2142","authenticated-orcid":false,"given":"Francois","family":"Bremond","sequence":"additional","affiliation":[{"name":"Inria Center at Université Côte d'Azur, 2004 Rte des Lucioles, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0107-7029","authenticated-orcid":false,"given":"Antitza","family":"Dantcheva","sequence":"additional","affiliation":[{"name":"Inria Center at Université Côte d'Azur, 2004 Rte des Lucioles, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref2","article-title":"OpenFace: A general-purpose face recognition library with mobile applications","author":"Amos","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_7"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref7","first-page":"31769","article-title":"Generating long videos of dynamic scenes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brooks"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601204"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00204"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref14","article-title":"Adversarial video generation on complex datasets","author":"Clark","year":"2019"},{"key":"ref15","first-page":"4417","article-title":"Unsupervised learning of disentangled representations from video","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00584"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref21","article-title":"Id-animator: Zero-shot identity-preserving human video generation","author":"He","year":"2024"},{"key":"ref22","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022"},{"key":"ref23","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref24","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref26","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"ref27","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref29","article-title":"On the \u201csteerability","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jahanian"},{"key":"ref30","first-page":"2225","article-title":"Video prediction with appearance and motion conditions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref35","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01723"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_37"},{"key":"ref38","first-page":"5670","article-title":"Disentangled sequential autoencoder","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref41","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11881"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00385"},{"key":"ref44","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_35"},{"key":"ref46","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref47","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"ref52","first-page":"7137","article-title":"First order motion model for image animation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Siarohin"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00452"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref57","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref59","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref60","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref64","article-title":"A good image generator is what you need for high-resolution video synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref66","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vondrick"},{"key":"ref67","article-title":"Unsupervised discovery of interpretable directions in the gan latent space","author":"Voynov","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.361"},{"key":"ref69","first-page":"5013","article-title":"Few-shot video-to-video synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref70","first-page":"1152","article-title":"Video-to-video synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref73","article-title":"Learning to generate human videos","author":"Wang","year":"2021"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00531"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref76","article-title":"InMoDeGAN: Interpretable motion decomposition generative adversarial network for video generation","author":"Wang","year":"2021"},{"key":"ref77","article-title":"LaVie: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3449075"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6931"},{"key":"ref81","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00535"},{"key":"ref84","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref87","article-title":"I2VGen-XL: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_24"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3014488"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10645735.pdf?arnumber=10645735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:32:55Z","timestamp":1732667575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":92,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3449075","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}