{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:05:28Z","timestamp":1780949128609,"version":"3.54.1"},"reference-count":124,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Australian Government through the Australian Research Council Discovery Project","award":["DP260100218"],"award-info":[{"award-number":["DP260100218"]}]},{"name":"NVIDIA Academic Hardware"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3664227","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:14Z","timestamp":1770929954000},"page":"7436-7450","source":"Crossref","is-referenced-by-count":0,"title":["Consistent and Controllable Image Animation With Linear Motion Diffusion Transformers"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9389-9032","authenticated-orcid":false,"given":"Xin","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9487-6187","authenticated-orcid":false,"given":"Yaohui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-138X","authenticated-orcid":false,"given":"Genyun","family":"Jia","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5517-7255","authenticated-orcid":false,"given":"Xinyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7792-9307","authenticated-orcid":false,"given":"Tien-Tsin","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2926-9762","authenticated-orcid":false,"given":"Cunjian","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref2","article-title":"SEINE: Short-to-long video diffusion model for generative transition and prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"PixArt: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref5","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref7","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole","year":"2023"},{"key":"ref8","article-title":"Instant3D: Fast text-to-3D with sparse-view generation and large reconstruction model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2024"},{"key":"ref9","first-page":"1","article-title":"Lavie: High-quality video generation with cascaded latent diffusion models","volume-title":"Int. J. Comput. Vis.","author":"Wang","year":"2024"},{"key":"ref10","article-title":"LATTE: Latent diffusion transformer for video generation","author":"Ma","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref13","article-title":"Make-a-Video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer","year":"2023"},{"key":"ref14","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guo","year":"2024"},{"key":"ref15","article-title":"AnimateAnything: Fine-grained open domain image animation with motion guidance","author":"Dai","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref17","article-title":"I2VGEN-XL: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref18","article-title":"ConsistI2V: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02129"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01696"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01175"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02603"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01165"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01174"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00728"},{"key":"ref27","article-title":"HunyuanVideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref28","article-title":"WAN: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"ref29","article-title":"Animating open-domain images with video diffusion priorsAnimating open-domain images with video diffusion priors","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2025"},{"key":"ref30","article-title":"Open-SORA Plan: Open-source large video generation model","author":"Lin","year":"2024"},{"key":"ref31","article-title":"Open-SORA: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref32","article-title":"LTX-Video: Realtime video latent diffusion","author":"HaCohen","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"ref35","first-page":"1","article-title":"Input perturbation reduces exposure bias in diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ning","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00683"},{"key":"ref37","article-title":"SANA: Efficient high-resolution image synthesis with linear diffusion transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2025"},{"key":"ref38","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref40","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref41","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref42","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref43","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"issue":"3","key":"ref45","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref46","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"ref49","article-title":"Training-free stylized text-to-image generation with fast inference","author":"Ma","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref52","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref53","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022"},{"key":"ref54","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Villegas","year":"2022"},{"key":"ref55","article-title":"Movie Gen: A cast of media foundation models","author":"Polyak","year":"2024"},{"key":"ref56","article-title":"Autoregressive video generation without vector quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Deng","year":"2025"},{"key":"ref57","article-title":"Pyramidal flow matching for efficient video generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jin","year":"2025"},{"key":"ref58","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Ho","year":"2022"},{"key":"ref59","article-title":"ImaGen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"issue":"47","key":"ref60","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02099"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275043"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3449075"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01964"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01486"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00052"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00513"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02231-3"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449075"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01965"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00517"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073273"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1409060.1409070"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00374"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12940"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112059"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-5577-0_18"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"ref82","first-page":"7594","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2024"},{"key":"ref83","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref84","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref85","first-page":"1","article-title":"AnimateLCM: Accelerating the animation of personalized diffusion models and adapters with decoupled consistency learning","volume-title":"Proc. SIGGRAPH Asia Tech. Commun.","author":"Wang","year":"2024"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887583"},{"key":"ref87","article-title":"VDT: General-purpose video diffusion transformers via mask modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref89","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref90","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Hu","year":"2024"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref92","first-page":"20662","article-title":"SnapFusion: Text-to-image diffusion model on mobile devices within two seconds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2023"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_13"},{"key":"ref94","article-title":"Bitsfusion: 1.99 bits weight quantization of diffusion model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sui","year":"2024"},{"key":"ref95","article-title":"LINFusion: 1 GPU, 1 minute, 16K image","author":"Liu","year":"2024"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00749"},{"key":"ref97","article-title":"Matten: Video generation with mamba-attention","author":"Gao","year":"2024"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00246"},{"key":"ref99","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu","year":"2024"},{"key":"ref100","first-page":"10041","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dao","year":"2024"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref102","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref106","article-title":"Exploring linear attention: Does attention really need a softmax?","author":"Jianlin","year":"2020"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref108","article-title":"ModelScope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref110","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hong","year":"2022"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00634"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref116","article-title":"FVD: A new metric for video generation","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Unterthiner","year":"2019"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"ref119","article-title":"GODIVA: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00738"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref123","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choromanski","year":"2021"},{"key":"ref124","article-title":"LinFormer: Self-attention with linear complexity (2020)","author":"Wang","year":"2006"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11393938.pdf?arnumber=11393938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:06Z","timestamp":1780948326000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11393938\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":124,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3664227","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":[[2026,7]]}}}