{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:34:46Z","timestamp":1782408886710,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991404"],"award-info":[{"award-number":["61991404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103092"],"award-info":[{"award-number":["62103092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991401"],"award-info":[{"award-number":["61991401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20189"],"award-info":[{"award-number":["U20A20189"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173120"],"award-info":[{"award-number":["62173120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Program of the Liaoning Liaohe Laboratory","award":["LLL23ZZ-05-01"],"award-info":[{"award-number":["LLL23ZZ-05-01"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["N2424004"],"award-info":[{"award-number":["N2424004"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3491865","type":"journal-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T18:37:05Z","timestamp":1730831825000},"page":"2632-2645","source":"Crossref","is-referenced-by-count":35,"title":["Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and Benchmark"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5149-2995","authenticated-orcid":false,"given":"Gaochang","family":"Wu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yapeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4830-9544","authenticated-orcid":false,"given":"Lan","family":"Deng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9450-188X","authenticated-orcid":false,"given":"Jingxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software and Electrical Engineering, Swinburne University of Technology, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-1483","authenticated-orcid":false,"given":"Tianyou","family":"Chai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2767545"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2566"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2349479"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ces.2010.10.008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3233668"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3070512"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3124015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3424435"},{"issue":"8","key":"ref11","first-page":"1475","article-title":"Abnormal condition diagnosis through deep learning of image sequences for fused magnesium furnaces","volume":"45","author":"Wu","year":"2019","journal-title":"Acta Autom. Sinica"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3168251"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref16","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref18","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3331841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2968516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2823766"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3140058"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"ref25","first-page":"1","article-title":"Anomaly transformer: Time series anomaly detection with association discrepancy","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183903"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00220"},{"key":"ref30","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2018.2838457"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01460"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01462"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3251395"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369656"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340102"},{"key":"ref42","article-title":"Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers","author":"Yang","year":"2021","journal-title":"arXiv:2107.03996"},{"key":"ref43","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3239908"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref47","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yang"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01876-w"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref53","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.362"},{"key":"ref56","first-page":"1","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref57","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref61","first-page":"24226","article-title":"Flowformer: Linearizing transformers with conservation flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref62","first-page":"1","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref63","article-title":"ITransformer: Inverted transformers are effective for time series forecasting","author":"Liu","year":"2023","journal-title":"arXiv:2310.06625"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01157"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10744600.pdf?arnumber=10744600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:49:14Z","timestamp":1741373354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10744600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":65,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3491865","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}