{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:08:05Z","timestamp":1781280485134,"version":"3.54.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["2022R1A5A8023404"],"award-info":[{"award-number":["2022R1A5A8023404"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Instrum. Meas."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tim.2025.3551832","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T23:29:32Z","timestamp":1743463772000},"page":"1-13","source":"Crossref","is-referenced-by-count":10,"title":["AADC-Net: A Multimodal Deep Learning Framework for Automatic Anomaly Detection in Real-Time Surveillance"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1042-5032","authenticated-orcid":false,"given":"Duc","family":"Tri Phan","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Pukyong National University, Busan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6393-9883","authenticated-orcid":false,"given":"Vu","family":"Hoang Minh Doan","sequence":"additional","affiliation":[{"name":"Smart Gym-Based Translational Research Center for Active Senior’s Healthcare, Pukyong National University, Busan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2370-3318","authenticated-orcid":false,"given":"Jaeyeop","family":"Choi","sequence":"additional","affiliation":[{"name":"Smart Gym-Based Translational Research Center for Active Senior’s Healthcare, Pukyong National University, Busan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1574-7145","authenticated-orcid":false,"given":"Byeongil","family":"Lee","sequence":"additional","affiliation":[{"name":"Digital Healthcare Research Center, Institute of Information Technology and Convergence, Pukyong National University, Busan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5837-0958","authenticated-orcid":false,"given":"Junghwan","family":"Oh","sequence":"additional","affiliation":[{"name":"Ohlabs Corporation, Busan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2020.2991008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104078"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-10464-0_11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3280508"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3282993"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3440374"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/23335777.2021.1940303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/01655515211022665"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-021-01586-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIRCA51532.2021.9544795"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION49465.2021.9626932"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3343832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3279422"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3338681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3318684"},{"issue":"3","key":"ref17","first-page":"8530","article-title":"Detection and classification of weightlifting form anomalies using deep learning","volume":"6","author":"Sapwan","year":"2022","journal-title":"J. Positive School Psychol."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3336758"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.36548\/jscp.2021.2.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.116066"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292596"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16001-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09277-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3066675"},{"key":"ref27","article-title":"Deep multi-scale video prediction beyond mean square error","author":"Mathieu","year":"2015","journal-title":"arXiv:1511.05440"},{"key":"ref28","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Larsen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3234974"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3040591"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00135"},{"key":"ref32","article-title":"Video anomaly detection and explanation via large language models","author":"Lv","year":"2024","journal-title":"arXiv:2401.05702"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01788"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/s23115024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13954-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16445-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01561"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3227044"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147369"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00724"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref47","article-title":"VideoChat: Chat-centric video understanding","author":"Li","year":"2023","journal-title":"arXiv:2305.06355"},{"key":"ref48","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv:2305.16355"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref50","article-title":"Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models","author":"Ning","year":"2023","journal-title":"arXiv:2311.16103"},{"key":"ref51","first-page":"8483","article-title":"Language models with image descriptors are strong few-shot video-language learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref53","article-title":"VideoGPT+: Integrating image and video encoders for enhanced video understanding","author":"Maaz","year":"2024","journal-title":"arXiv:2406.09418"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.009"},{"key":"ref56","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":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref58","article-title":"EfficientCLIP: Efficient cross-modal pre-training by ensemble confident learning and language modeling","author":"Wang","year":"2021","journal-title":"arXiv:2109.04699"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref65","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00321"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00829"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107515"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ61134.2023.10343675"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"ref73","first-page":"338","article-title":"Consistency-based self-supervised learning for temporal anomaly localization","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Panariello"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3462433"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01219"}],"container-title":["IEEE Transactions on Instrumentation and Measurement"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/19\/10764799\/10946244.pdf?arnumber=10946244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T04:49:18Z","timestamp":1744951758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10946244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tim.2025.3551832","relation":{},"ISSN":["0018-9456","1557-9662"],"issn-type":[{"value":"0018-9456","type":"print"},{"value":"1557-9662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}