{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:24:21Z","timestamp":1774679061127,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB3102600"],"award-info":[{"award-number":["2022YFB3102600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272374"],"award-info":[{"award-number":["62272374"]}],"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":["62192781"],"award-info":[{"award-number":["62192781"]}],"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":["62202367"],"award-info":[{"award-number":["62202367"]}],"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":["62250009"],"award-info":[{"award-number":["62250009"]}],"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":["62137002"],"award-info":[{"award-number":["62137002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Knowledge Center for Engineering Science and Technology"},{"DOI":"10.13039\/501100019069","name":"Chinese Academy of Engineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012692","name":"K. C. Wong Education Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012692","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3371220","type":"journal-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T18:56:14Z","timestamp":1709146574000},"page":"7761-7774","source":"Crossref","is-referenced-by-count":15,"title":["Noise-Tolerant Learning for Audio-Visual Action Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0479-8932","authenticated-orcid":false,"given":"Haochen","family":"Han","sequence":"first","affiliation":[{"name":"National Engineering Lab for Big Data Analytics, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8436-4754","authenticated-orcid":false,"given":"Qinghua","family":"Zheng","sequence":"additional","affiliation":[{"name":"National Engineering Lab for Big Data Analytics, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-7860","authenticated-orcid":false,"given":"Minnan","family":"Luo","sequence":"additional","affiliation":[{"name":"National Engineering Lab for Big Data Analytics, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8579-1750","authenticated-orcid":false,"given":"Kaiyao","family":"Miao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Networks and Network Security (Xi'an Jiaotong University), Ministry of Education, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7888-0587","authenticated-orcid":false,"given":"Feng","family":"Tian","sequence":"additional","affiliation":[{"name":"National Engineering Lab for Big Data Analytics, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4838-3779","authenticated-orcid":false,"given":"Yan","family":"Chen","sequence":"additional","affiliation":[{"name":"National Engineering Lab for Big Data Analytics, Xi'an Jiaotong University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"YouTube-8 m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref2","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Alwassel","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref5","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref7","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref9","article-title":"Learning with instance-dependent label noise: A sample sieve approach","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheng","year":"2021"},{"key":"ref10","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref12","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Jort","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref14","article-title":"Masking: A new perspective of noisy supervision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Han","year":"2018"},{"key":"ref15","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Han","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247939"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00536"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177356"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00342"},{"key":"ref20","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Huang","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00945"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref24","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref25","article-title":"A method for stochastic optimizations","volume-title":"Proc. Int. Conf. Learn. Represent.","volume":"5","author":"Kinga","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_8"},{"key":"ref29","article-title":"Dividemix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5898"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2871418"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3073248"},{"key":"ref37","first-page":"6543","article-title":"Normalized loss functions for deep learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00748"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2446462"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref42","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref44","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Shu","year":"2019"},{"key":"ref45","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00524"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00555"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref50","article-title":"Representation learning with contrastive predictive coding","author":"Van den Oord","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref54","article-title":"Rethinking spatiotemporal feature learning for video understanding","author":"Xie","year":"2017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127346"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00119"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877939"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3134156"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183586"},{"key":"ref61","article-title":"Learning with feature-dependent label noise: A progressive approach","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2021"},{"key":"ref62","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zhang","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17319"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10452819.pdf?arnumber=10452819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:51:55Z","timestamp":1714762315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10452819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3371220","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}