{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:00:45Z","timestamp":1785474045653,"version":"3.56.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":[[2026,6]]},"DOI":"10.1109\/iv66570.2026.11623870","type":"proceedings-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T19:09:57Z","timestamp":1785438597000},"page":"1287-1294","source":"Crossref","is-referenced-by-count":0,"title":["LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation"],"prefix":"10.1109","author":[{"given":"Mirlan","family":"Karimov","sequence":"first","affiliation":[{"name":"Mercedes-Benz AG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teodora","family":"Spasojevi\u0107","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Braun","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Wiederer","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasileios","family":"Belagiannis","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref3","article-title":"Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion","author":"Luo","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02612"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02612"},{"key":"ref8","article-title":"DiVE: DiT-based Video Generation with Enhanced Control","author":"Jiang","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","article-title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","volume-title":"ICLR","author":"Yu"},{"key":"ref13","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2023"},{"key":"ref14","article-title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","volume-title":"ICLR","author":"Namekata"},{"key":"ref15","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref19","article-title":"Imagen Video: High Definition Video Generation with Diffusion Models","author":"Ho","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref22","article-title":"Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models","author":"Mousakhan","year":"2025"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-73229-4_27","article-title":"DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model","volume-title":"ECCV","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00780"},{"key":"ref26","article-title":"GAIA-1: A Generative World Model for Autonomous Driving","author":"Hu","year":"2023"},{"key":"ref27","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref29","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of Machine Learning Research","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2906"},{"key":"ref32","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref33","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"ICLR","author":"Hu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref36","article-title":"Towards accurate generative models of video: A new metric\u2019 challenges","author":"Unterthiner","year":"2019"},{"key":"ref37","first-page":"6626","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":"ref38","article-title":"DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes","author":"Mei","year":"2024"},{"key":"ref39","article-title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","volume-title":"ICLR","author":"Gao"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02561"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref45","article-title":"YOLOv11: An Overview of the Key Architectural Enhancements","author":"Khanam","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"}],"event":{"name":"2026 IEEE Intelligent Vehicles Symposium (IV)","location":"Plymouth, MI, USA","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,25]]}},"container-title":["2026 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11623815\/11623816\/11623870.pdf?arnumber=11623870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T04:46:37Z","timestamp":1785473197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11623870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iv66570.2026.11623870","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}