{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:32:25Z","timestamp":1770748345634,"version":"3.50.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3294977","type":"journal-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T17:33:02Z","timestamp":1689269582000},"page":"6646-6660","source":"Crossref","is-referenced-by-count":8,"title":["The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1604-9178","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"first","affiliation":[{"name":"China Academy of Railway Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3744-2254","authenticated-orcid":false,"given":"Zheng","family":"Tang","sequence":"additional","affiliation":[{"name":"NVIDIA, Redmond, WA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202574"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"ref3","article-title":"Exploiting completeness and uncertainty of pseudo labels for weakly supervised video anomaly detection","author":"Zhang","year":"2022","journal-title":"arXiv:2212.04090"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"5","key":"ref5","first-page":"6","article-title":"Train intelligent testing system based on convolution neural network optimization algorithm","volume":"28","author":"Wang","year":"2019","journal-title":"Railway Comput. Appl."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-021-01729-0"},{"key":"ref7","first-page":"120","article-title":"Towards cross-modal causal structure and representation learning","volume-title":"Proc. Mach. Learn. Health","author":"Mao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref10","article-title":"Local-global context aware transformer for language-guided video segmentation","author":"Liang","year":"2022","journal-title":"arXiv:2203.09773"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123456"},{"key":"ref13","article-title":"Learning equivariant segmentation with instance-unique querying","author":"Wang","year":"2022","journal-title":"arXiv:2210.00911"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230064"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"ref17","article-title":"Visual recognition with deep nearest centroids","author":"Wang","year":"2022","journal-title":"arXiv:2209.07383"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105632"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2018.00022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00900"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00030"},{"issue":"7","key":"ref24","first-page":"30","article-title":"CBTC software intelligent test system technology based on big data computing model","volume":"29","author":"Chao","year":"2020","journal-title":"Railway Comput. Appl."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9411961"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524717"},{"key":"ref27","article-title":"Fusion is not enough: Single-modal attacks to compromise fusion models in autonomous driving","author":"Cheng","year":"2023","journal-title":"arXiv:2304.14614"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref29","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref30","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv:1612.03928"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref33","first-page":"1","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kim"},{"key":"ref34","article-title":"A neural algorithm of artistic style","author":"Gatys","year":"2015","journal-title":"arXiv:1508.06576"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015628"},{"key":"ref38","article-title":"FEED: Feature-level ensemble for knowledge distillation","author":"Park","year":"2019","journal-title":"arXiv:1909.10754"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3007506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"ref41","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371792"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00128"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022859003006"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803657"},{"key":"ref54","article-title":"Motion-aware feature for improved video anomaly detection","author":"Zhu","year":"2019","journal-title":"arXiv:1907.10211"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref56","first-page":"2223","article-title":"Unpaired image-to-image translation using cycleconsistent adversarial networks","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Rai"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref59","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref61","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref62","first-page":"1","article-title":"Contrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tian"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10182291.pdf?arnumber=10182291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:38:34Z","timestamp":1736368714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10182291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":66,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3294977","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}