{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:46:30Z","timestamp":1770281190672,"version":"3.49.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018696","name":"Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018696","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610149","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"14645-14652","source":"Crossref","is-referenced-by-count":1,"title":["TiV-ODE: A Neural ODE-based Approach for Controllable Video Generation From Text-Image Pairs"],"prefix":"10.1109","author":[{"given":"Yucheng","family":"Xu","sequence":"first","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Nanbo","family":"Li","sequence":"additional","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Arushi","family":"Goel","sequence":"additional","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Zonghai","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Massachusetts-Amherst,College of Information and Computing Sciences,US"}]},{"given":"Zijian","family":"Guo","sequence":"additional","affiliation":[{"name":"Boston University,Department of Electrical and Computer Engineering,US"}]},{"given":"Hamidreza","family":"Kasaei","sequence":"additional","affiliation":[{"name":"University of Groningen,Department of Artificial Intelligence, Bernoulli Institute,The Netherlands"}]},{"given":"Mohammadreza","family":"Kasaei","sequence":"additional","affiliation":[{"name":"University of Edinburgh,School of Informatics,UK"}]},{"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[{"name":"University College,Department of Computer Science,London,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00715"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9671"},{"key":"ref4","article-title":"Learning universal policies via text-guided video generation","author":"Dai","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3272516\/mm1"},{"key":"ref6","article-title":"See, plan, predict: Language-guided cognitive planning with video prediction","author":"Attarian","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00819"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01334-x"},{"key":"ref10","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123309"},{"key":"ref12","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16342"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00513"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2987316"},{"key":"ref17","article-title":"Antisymmetricrnn: A dynamical system view on recurrent neural networks","author":"Chang","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1201\/9780429492563"},{"key":"ref19","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"ref21","first-page":"6140","article-title":"Improving generative imagination in object-centric world models","volume-title":"International Conference on Machine Learning","author":"Lin"},{"key":"ref22","article-title":"Conditional object-centric learning from video","author":"Kipf","year":"2021"},{"key":"ref23","first-page":"10 772","article-title":"Object-centric representation learning with generative spatial-temporal factorization","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Slotformer: Unsupervised visual dynamics simulation with object-centric models","author":"Wu","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.119"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2934852"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","article-title":"Latent ordinary differential equations for irregularly-sampled time series","volume":"32","author":"Rubanova","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Gru-ode-bayes: Continuous modeling of sporadically-observed time series","volume":"32","author":"De Brouwer","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Ode2vae: Deep generative second order odes with bayesian neural networks","volume":"32","author":"Yildiz","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Universal approximation property of neural ordinary differential equations","author":"Teshima","year":"2020"},{"key":"ref32","first-page":"11 086","article-title":"Approximation capabilities of neural odes and invertible residual networks","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref33","article-title":"Simple video generation using neural odes","author":"Kanaa","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref36","article-title":"Cater: A diagnostic dataset for compositional actions and temporal reasoning","author":"Girdhar","year":"2019"},{"key":"ref37","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"Mlim: Vision-and-language model pre-training with masked language and image modeling","author":"Arici","year":"2021"},{"key":"ref41","article-title":"Theory and experiments on vector quantized autoencoders","author":"Roy","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-020-00360-2"},{"key":"ref43","article-title":"Augmented neural odes","volume":"32","author":"Dupont","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0771-050X(80)90013-3"},{"key":"ref45","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022"},{"key":"ref46","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref48","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref49","article-title":"Generating images with perceptual similarity metrics based on deep networks","volume":"29","author":"Dosovitskiy","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04101"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610149.pdf?arnumber=10610149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:44:56Z","timestamp":1723268696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610149\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610149","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}