{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:08Z","timestamp":1757608688564,"version":"3.44.0"},"reference-count":56,"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\/icra55743.2025.11128056","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8412-8419","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Conditioned Temporal Diffusion Modeling for Driving Scene Generation"],"prefix":"10.1109","author":[{"given":"Xiangyu","family":"Bai","sequence":"first","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,Massachusetts,USA,02115"}]},{"given":"Yedi","family":"Luo","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,Massachusetts,USA,02115"}]},{"given":"Le","family":"Jiang","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,Massachusetts,USA,02115"}]},{"given":"Sarah","family":"Ostadabbas","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,Massachusetts,USA,02115"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812276"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096852"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3633463"},{"journal-title":"Midas v3.1 - a model zoo for robust monocular relative depth estimation","year":"2023","author":"Birkl","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"journal-title":"Jimeng ai: Instant creation from your inspiration","year":"2024","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"108412","DOI":"10.1016\/j.dib.2022.108412","article-title":"Gtasynth: 3d synthetic data of outdoor non-urban environments","volume":"43","author":"Curnis","year":"2022","journal-title":"Data in Brief"},{"key":"ref10","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148457"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.195"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02385"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"volume-title":"evo: Python package for the evaluation of odometry and slam","year":"2017","author":"Grupp","key":"ref17"},{"key":"ref18","article-title":"Waymax: An accelerated, data-driven simulator for large-scale autonomous driving research","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Gulino","year":"2023"},{"key":"ref19","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":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00519"},{"journal-title":"July2021, if you use this software, please cite it as below","article-title":"Openclip","author":"Ilharco","key":"ref23"},{"article-title":"Prior-aware synthetic data to the rescue: Animal pose estimation with very limited real data","volume-title":"The British Machine Vision Conference (BMVC)","author":"Jiang","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s24010108"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00498"},{"journal-title":"Kling ai - powerful ai video generator by the kuaishou team","year":"2024","author":"Kuaishou","key":"ref28"},{"journal-title":"Magicedit: Highfidelity and temporally coherent video editing","year":"2023","author":"Liew","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00560"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00655"},{"key":"ref32","article-title":"Temporal-controlled frame swap for generating highfidelity stereo driving data for autonomy analysis","volume-title":"British Machine Vision Conference","author":"Luo","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00861"},{"journal-title":"Video generation models as world simulators","year":"2024","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02672"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/airc64931.2025.11077565"},{"key":"ref38","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594299"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341176"},{"journal-title":"Make-a-video: Text-to-video generation without text-video data","year":"2022","author":"Singer","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref45","article-title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","author":"Teed","year":"2021","journal-title":"Advances in neural information processing systems"},{"journal-title":"Towards accurate generative models of video: A new metric & challenges","year":"2018","author":"Unterthiner","key":"ref46"},{"journal-title":"Gen-lvideo: Multi-text to long video generation via temporal co-denoising","year":"2023","author":"Wang","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/569\/3\/032035"},{"journal-title":"Introducing gaia-1: A generative ai model for autonomy","year":"2023","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00701"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"journal-title":"Cogvideox: Text-tovideo diffusion models with an expert transformer","year":"2024","author":"Yang","key":"ref52"},{"journal-title":"Alita: A large-scale incremental dataset for long-term autonomy","year":"2022","author":"Yin","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02539"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"journal-title":"Controlvideo: Training-free controllable text-to-video generation","year":"2023","author":"Zhang","key":"ref56"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128056.pdf?arnumber=11128056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:12:18Z","timestamp":1756879938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128056","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}