{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:44:46Z","timestamp":1778600686768,"version":"3.51.4"},"reference-count":67,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01121","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12057-12067","source":"Crossref","is-referenced-by-count":1,"title":["Autoregressive Denoising Score Matching Is a Good Video Anomaly Detector"],"prefix":"10.1109","author":[{"given":"Hanwen","family":"Zhang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"}]},{"given":"Congqi","family":"Cao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"}]},{"given":"Qinyi","family":"Lv","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"}]},{"given":"Lingtong","family":"Min","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"}]},{"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref3","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"International Conference on Machine Learning","author":"Bao","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103656"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16177"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01953"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372466"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3461718"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_20"},{"key":"ref11","article-title":"MMTracking Contributors","volume-title":"Mmtracking: Openmmlab video perception toolbox and benchmark","year":"2020"},{"key":"ref12","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3039899"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00947"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074805"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01246"},{"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"},{"issue":"4","key":"ref21","article-title":"Estimation of nonnormalized statistical models by score matching","volume":"6","author":"Dayan","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00050-1"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130545"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISIP.2010.63"},{"key":"ref28","first-page":"276","article-title":"A kernelized stein discrepancy for goodness-of-fit tests","volume-title":"International conference on machine learning","author":"Liu","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3205348"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129349"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681120"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00938"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01517"},{"key":"ref38","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Multiscale score matching for out-of-distribution detection","author":"Mahmood","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Deep multi-scale video prediction beyond mean square error","author":"Mathieu","year":"2015","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01785"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2973"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00136"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref45","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3040591"},{"key":"ref48","article-title":"Attribute-based representations for accurate and interpretable video anomaly detection","author":"Reiss","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01513"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093633"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2950530"},{"key":"ref53","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems, 32"},{"key":"ref54","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02188"},{"key":"ref56","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_29"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933554"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01402"},{"key":"ref62","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01419"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2016.06.007"},{"key":"ref67","article-title":"Motion-aware feature for improved video anomaly detection","author":"Zhu","journal-title":"arXiv preprint"}],"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\/11445342.pdf?arnumber=11445342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:40Z","timestamp":1777529920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01121","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}