{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:42:43Z","timestamp":1778258563238,"version":"3.51.4"},"reference-count":89,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["W2411052,62273057"],"award-info":[{"award-number":["W2411052,62273057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01043","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11208-11218","source":"Crossref","is-referenced-by-count":1,"title":["Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis"],"prefix":"10.1109","author":[{"given":"Lei-Lei","family":"Li","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Fang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbin","family":"Xiao","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanmin","family":"Pang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongkai","family":"Yu","sequence":"additional","affiliation":[{"name":"Cleveland State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01293"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00752"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645610"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.85"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01073"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01230"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00882"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27899"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2915540"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341782"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917218"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3044678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02080"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564543"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3177640"},{"key":"ref20","author":"Gao","year":"2024","journal-title":"ICLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00382"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688119"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00751"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Videoshield: Regulating diffusionbased video generation models via watermarking","author":"Hu","year":"2025","journal-title":"ICLR"},{"key":"ref28","article-title":"Free-bloom: Zero-shot text-to-video generator with 11 m director and 1 dm animator","volume":"36","author":"Huang","year":"2024","journal-title":"NeurIPS"},{"key":"ref29","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2017","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/e26070556"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240780"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127968"},{"key":"ref35","article-title":"T2v-turbo-v2: Enhancing video generation model post-training through data, reward, and conditional guidance design","author":"Li","year":"2025","journal-title":"ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2024.3378460"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29269"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548035"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"ref42","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2025","journal-title":"ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.63317\/3i3wr3qopks4"},{"key":"ref44","article-title":"Causality compensated attention for contextual biased visual recognition","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref48","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"CoRR, abs\/2401.03048"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29840"},{"key":"ref50","article-title":"Stealing stable diffusion prior for robust monocular depth estimation","author":"Mao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00456-w"},{"key":"ref52","article-title":"Driver attention tracking and analysis","author":"Nguyen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2845370"},{"key":"ref54","article-title":"Generating driving scenes with diffusion","author":"Pronovost","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00059-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","first-page":"647668","article-title":"Diffusion causal models for counterfactual estimation","author":"Sanchez","year":"2022","journal-title":"CLeaR"},{"key":"ref60","article-title":"Diffusion models for causal discovery via topological ordering","author":"Sanchez","year":"2023","journal-title":"ICLR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921777"},{"key":"ref62","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref63","article-title":"Text2street: Controllable text-to-image generation for street views","author":"Su","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Add-it: Training-free object insertion in images with pretrained diffusion models","author":"Tewel","year":"2025","journal-title":"ICLR"},{"key":"ref65","volume-title":"U. s. news, 10 vehicles that are almost selfdriving in 2024","author":"Threewitt","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105716"},{"key":"ref67","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"CoRR, abs\/1812.01717"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00207"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170302"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref71","article-title":"Lavie: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"ref72","article-title":"Detail-enhancing framework for reference-based image super-resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00677"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_42"},{"key":"ref77","article-title":"Versvideo: Leveraging enhanced temporal diffusion models for versatile video generation","author":"Xiang","year":"2023","journal-title":"ICLR"},{"key":"ref78","article-title":"Video diffusion models are training-free motion interpreter and controller","author":"Xiao","year":"2024","journal-title":"CoRR, abs\/2405.14864"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00085"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3121705"},{"key":"ref81","author":"Yang","year":"2025","journal-title":"Videograin: Modulating space-time attention for multigrained video editing"},{"key":"ref82","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2025","journal-title":"ICLR"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28489"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00059"},{"key":"ref85","article-title":"Boosting causal discovery via adaptive sample reweighting","author":"Zhang","year":"2023","journal-title":"ICLR"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11229-023-04237-9"},{"key":"ref87","article-title":"Controlvideo: Trainingfree controllable text-to-video generation","author":"Zhang","year":"2024","journal-title":"ICLR"},{"key":"ref88","article-title":"Towards consistent video editing with text-to-image diffusion models","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref89","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","author":"Zhou","year":"2024","journal-title":"ICLR"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444050.pdf?arnumber=11444050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:34Z","timestamp":1777611574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01043","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}