{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T02:15:21Z","timestamp":1778552121210,"version":"3.51.4"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","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"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0210700"],"award-info":[{"award-number":["2024YFE0210700"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62273057"],"award-info":[{"award-number":["62273057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Outstanding Youth Foundation of Shaanxi Province","award":["2025JC-JCQN-092"],"award-info":[{"award-number":["2025JC-JCQN-092"]}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Program of Shaanxi","doi-asserted-by":"crossref","award":["2025PT-ZCK-66"],"award-info":[{"award-number":["2025PT-ZCK-66"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3663545","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:55:51Z","timestamp":1770843351000},"page":"6980-6998","source":"Crossref","is-referenced-by-count":0,"title":["ADVersa: Abductive Driving Accident Video Understanding"],"prefix":"10.1109","volume":"48","author":[{"given":"Lei-Lei","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0300-6892","authenticated-orcid":false,"given":"Jianwu","family":"Fang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbin","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-8913","authenticated-orcid":false,"given":"Hongkai","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Cleveland State University, Cleveland, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6897-4512","authenticated-orcid":false,"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4994-9343","authenticated-orcid":false,"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4525-1204","authenticated-orcid":false,"given":"Zhengguo","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00456-w"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3355812"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02080"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3150763"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3275543"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3044678"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2024.3378460"},{"key":"ref9","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"},{"key":"ref10","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00090"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01043"},{"key":"ref14","article-title":"Ctrl-Crash: Controllable diffusion for realistic car crashes","author":"Gosselin","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127968"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00707"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00708"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3323085"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3572682"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00698"},{"key":"ref24","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Prof. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00978"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32951"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01118"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02659"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref30","article-title":"Show-o2: Improved native unified multimodal models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2025"},{"key":"ref31","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2025"},{"key":"ref32","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54190-7_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967556"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301978"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_32"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413827"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3115123"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28370"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094809"},{"key":"ref42","article-title":"COOOL: Challenge of out-of-label a novel benchmark for autonomous driving","author":"AlShami","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00651"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01770"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01779"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2939"},{"key":"ref48","article-title":"Finding the trigger: Causal abductive reasoning on video events","author":"Le","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681244"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-025-01683-y"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.254"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_7419"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00800"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00579"},{"key":"ref55","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00271"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref61","article-title":"Tracking anything in high quality","author":"Zhu","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917218"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00466"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref68","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref71","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref73","first-page":"98478","article-title":"Scene graph disentanglement and composition for generalizable complex image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2024"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_42"},{"key":"ref76","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1698"},{"key":"ref78","article-title":"Long-context autoregressive video modeling with next-frame prediction","author":"Gu","year":"2025"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2003.819861"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref82","first-page":"76115","article-title":"Video diffusion models are training-free motion interpreter and controller","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiao","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref85","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref87","article-title":"Add-it: Training-free object insertion in images with pretrained diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tewel","year":"2025"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref89","article-title":"ControlVideo: Training-free controllable text-to-video generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref90","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2022"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02126"},{"key":"ref92","article-title":"Seer: Language instructed video prediction with latent diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2024"},{"key":"ref93","article-title":"World simulation with video foundation models for physical AI","author":"Ali","year":"2025"},{"key":"ref94","article-title":"InternVL3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency","author":"Wang","year":"2025"},{"key":"ref95","article-title":"Mobile-videoGPT: Fast and accurate video understanding language model","author":"Shaker","year":"2025"},{"key":"ref96","article-title":"LLaVA-mini: Efficient image and video large multimodal models with one vision token","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2025"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1138"},{"key":"ref99","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref100","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2025"},{"key":"ref101","article-title":"MotionClone: Training-free motion cloning for controllable video generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ling","year":"2025"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00677"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00954"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11391656.pdf?arnumber=11391656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:53:24Z","timestamp":1778550804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391656\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":104,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3663545","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}