{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:24:41Z","timestamp":1774365881053,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128780","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"12842-12849","source":"Crossref","is-referenced-by-count":4,"title":["This&That: Language-Gesture Controlled Video Generation for Robot Planning"],"prefix":"10.1109","author":[{"given":"Boyang","family":"Wang","sequence":"first","affiliation":[{"name":"University of Michigan"}]},{"given":"Nikhil","family":"Sridhar","sequence":"additional","affiliation":[{"name":"University of Michigan"}]},{"given":"Chao","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Michigan"}]},{"given":"Mark","family":"van der Merwe","sequence":"additional","affiliation":[{"name":"University of Michigan"}]},{"given":"Adam","family":"Fishman","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Nima","family":"Fazeli","sequence":"additional","affiliation":[{"name":"University of Michigan"}]},{"given":"Jeong Joon","family":"Park","sequence":"additional","affiliation":[{"name":"University of Michigan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning to act from actionless videos through dense correspondences","author":"Ko","year":"2023","journal-title":"ar Xiv preprint arXiv"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Learning interactive real-world simulators","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"1723","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning","author":"Walke","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref6","author":"Shridhar","year":"2022","journal-title":"Perceiver-actor: A multi-task transformer for robotic manipulation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref10","article-title":"Implicit behavioral cloning","volume-title":"Conference on Robot Learning (CoRL)","author":"Florence","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3295255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.047"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.082"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8794143"},{"key":"ref17","author":"Sundaresan","year":"2024","journal-title":"Rt-sketch: Goal-conditioned imitation learning from hand-drawn sketches"},{"key":"ref18","author":"Jang","year":"2022","journal-title":"Bc-z: Zero-shot task generalization with robotic imitation learning"},{"key":"ref19","article-title":"Robust manipulation with spatial features","volume-title":"CoRL 2022 Workshop on Pre-training Robot Learning","author":"Burns","year":"2022"},{"key":"ref20","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref22","article-title":"Consisti2v: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00245"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref26","article-title":"Drag any thing: Motion control for anything using entity representation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Follow-your-click: Open-domain regional image animation via short prompts","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref29","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref32","article-title":"Animate any-one: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Motionctrl: A unified and flexible motion controller for video generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Learning universal policies via text-guided video generation","volume":"36","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","article-title":"Robo-dreamer: Learning compositional world models for robot imagination","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Video language planning","author":"Du","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Moka: Open-vocabulary robotic manipulation through mark-based visual prompting","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref41","article-title":"Tokenlearner: What can 8 learned tokens do for images and videos?","author":"Ryoo","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","volume-title":"pytorch-fid: FID Score for PyTorch","author":"Seitzer","year":"2020"},{"key":"ref45","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref47","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref48","volume-title":"Evaluating the ability of large language models to reason about cardinal directions","author":"Cohn","year":"2024"},{"key":"ref49","volume-title":"Is a picture worth a thousand words? delving into spatial reasoning for vision language models","author":"Wang","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128780.pdf?arnumber=11128780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:35Z","timestamp":1756880015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128780","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}