{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:37:11Z","timestamp":1780105031669,"version":"3.54.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Project of Shenzhen Science and Technology Plan","award":["20220810180617001"],"award-info":[{"award-number":["20220810180617001"]}]},{"name":"Foundation for Science and Technology Innovation of Shenzhen","award":["RCBS20210609103708014"],"award-info":[{"award-number":["RCBS20210609103708014"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515010645"],"award-info":[{"award-number":["2022A1515010645"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Project Programme of the State Key Laboratory of Internet of Things for Smart City","award":["SKLIoTSC(UM)-2021-2023\/ORP\/GA04\/2022"],"award-info":[{"award-number":["SKLIoTSC(UM)-2021-2023\/ORP\/GA04\/2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3390173","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T17:40:39Z","timestamp":1713375639000},"page":"8684-8697","source":"Crossref","is-referenced-by-count":19,"title":["Text-Driven Traffic Anomaly Detection With Temporal High-Frequency Modeling in Driving Videos"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7313-6561","authenticated-orcid":false,"given":"Rongqin","family":"Liang","sequence":"first","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4526-3018","authenticated-orcid":false,"given":"Yuanman","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6015-2618","authenticated-orcid":false,"given":"Jiantao","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City and the Department of Computer and Information Science, University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8043-9966","authenticated-orcid":false,"given":"Xia","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2913998"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2539684"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935195"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2601655"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3147826"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3150763"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59081-3_23"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3157254"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref14","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. conf. mach. learn.","volume":"139","author":"Jia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"ref16","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321503"},{"key":"ref19","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3357977"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3044678"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3190539"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3148392"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3134410"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3159538"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icme52920.2022.9860012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3355143"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.12.017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967556"},{"key":"ref33","article-title":"Anomaly crossing: New horizons for video anomaly detection as cross-domain few-shot learning","author":"Sun","year":"2021","journal-title":"arXiv:2112.06320"},{"key":"ref34","article-title":"A memory-augmented multitask collaborative framework for unsupervised traffic accident detection in driving videos","author":"Liang","year":"2023","journal-title":"arXiv:2307.14575"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3294998"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01059"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00743"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"ref53","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2984783"},{"key":"ref56","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10504300.pdf?arnumber=10504300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,5]],"date-time":"2024-10-05T06:44:20Z","timestamp":1728110660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":56,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3390173","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}