{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:13:50Z","timestamp":1778051630504,"version":"3.51.4"},"reference-count":75,"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"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00321","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3285-3296","source":"Crossref","is-referenced-by-count":0,"title":["Show Me: Unifying Instructional Image and Video Generation with Diffusion Models"],"prefix":"10.1109","author":[{"given":"Yujiang","family":"Pu","sequence":"first","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanbo","family":"Huang","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishnu","family":"Boddeti","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Kong","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref3","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02106"},{"key":"ref10","article-title":"Seine: Short-to-long video diffusion model for generative transition and prediction","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen"},{"key":"ref11","author":"Clark","year":"2023","journal-title":"Directly fine-tuning diffusion models on differentiable rewards"},{"key":"ref12","author":"Dai","year":"2023","journal-title":"Animateanything: Fine-grained open domain image animation with motion guidance"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref18","author":"Gu","year":"2023","journal-title":"Seer: Language instructed video prediction with latent diffusion models"},{"key":"ref19","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref20","author":"Hertz","year":"2022","journal-title":"Prompt-to-prompt image editing with cross attention control"},{"key":"ref21","first-page":"30","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref26","author":"H\u00f6ppe","year":"2022","journal-title":"Diffusion models for video prediction and infilling"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-35280-8_1432"},{"key":"ref28","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":"ref29","author":"Hu","year":"2023","journal-title":"Videocontrolnet: A motion-guided video-to-video translation framework by using diffusion model with controlnet"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"ref32","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1202"},{"key":"ref34","first-page":"135","article-title":"Lego: L earning ego centric action frame generation via visual instruction tuning","volume-title":"European Conference on Computer Vision","author":"Lai"},{"key":"ref35","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0550"},{"key":"ref38","first-page":"366","article-title":"Evaluating text-to-visual generation with image-to-text generation","volume-title":"European Conference on Computer Vision","author":"Lin"},{"key":"ref39","first-page":"36","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref40","author":"Lu","year":"2023","journal-title":"Vdt: General-purpose video diffusion transformers via mask modeling"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref42","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00600"},{"key":"ref44","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref45","author":"Prabhudesai","year":"2023","journal-title":"Aligning text-to-image diffusion models with reward backpropagation"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref48","author":"Ren","year":"2024","journal-title":"Consisti2v: Enhancing visual consistency for image-to-video generation"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref51","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref52","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref53","author":"Song","year":"2020","journal-title":"Score-based generative modeling through stochastic differential equations"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00627"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02555"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref57","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref58","author":"Unterthiner","year":"2018","journal-title":"Towards accurate generative models of video: A new metric & challenges"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1698"},{"key":"ref60","first-page":"36","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume-title":"Advances in Neural Information Processing Systems","author":"Wang","year":"2024"},{"key":"ref61","author":"Wang","year":"2023","journal-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref66","author":"Xing","year":"2024","journal-title":"Aid: Adapting image2video diffusion models for instruction-guided video prediction"},{"key":"ref67","first-page":"36","article-title":"Imagere-ward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"ref69","author":"Yang","year":"2023","journal-title":"Learning interactive real-world simulators"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref73","volume-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01827"},{"key":"ref75","first-page":"36","article-title":"Towards consistent video editing with text-to-image diffusion models","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11492407.pdf?arnumber=11492407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:20:13Z","timestamp":1778048413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00321","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}