{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:48:22Z","timestamp":1783788502502,"version":"3.55.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41776142"],"award-info":[{"award-number":["41776142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3109102","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T21:09:12Z","timestamp":1630357752000},"page":"123977-123986","source":"Crossref","is-referenced-by-count":90,"title":["TransAnomaly: Video Anomaly Detection Using Video Vision Transformer"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6869-9159","authenticated-orcid":false,"given":"Hongchun","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0785-1425","authenticated-orcid":false,"given":"Zhenyu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9370-9403","authenticated-orcid":false,"given":"Hui","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6754-5246","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6700-5960","authenticated-orcid":false,"given":"Xiangzhi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993373"},{"key":"ref32","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2016","journal-title":"ArXiv 1611 07004"},{"key":"ref31","first-page":"528","article-title":"Learning joint spatial-temporal transformations for video inpainting","author":"zeng","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref30","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123451"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350899"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.11.024"},{"key":"ref14","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref19","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2018","journal-title":"arXiv 1805 08318"},{"key":"ref28","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"chen","year":"2021","journal-title":"arXiv 2102 04306"},{"key":"ref4","first-page":"189","article-title":"Abnormal event detection in videos using spatiotemporal autoencoder","author":"chong","year":"2017","journal-title":"Proc Int Symp Neural Netw"},{"key":"ref27","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"arXiv 2010 04159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00136"},{"key":"ref29","first-page":"6881","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"zheng","year":"2021","journal-title":"Proc IEEE Conf Vis Pattern Recognit (CVPR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102920"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104078"},{"key":"ref9","article-title":"Anomaly detection in video using predictive convolutional long short-term memory networks","author":"medel","year":"2016","journal-title":"arXiv 1612 00390"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref22","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref23","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"arXiv 2005 14165"},{"key":"ref26","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref25","article-title":"ViViT: A video vision transformer","author":"arnab","year":"2021","journal-title":"arXiv 2103 15691"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09525368.pdf?arnumber=9525368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T19:53:52Z","timestamp":1643399632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3109102","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}