{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:34:08Z","timestamp":1726014848590},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651049","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Video Highlight Detection with Noise-Robust Learning"],"prefix":"10.1109","author":[{"given":"Yinhui","family":"Jiang","sequence":"first","affiliation":[{"name":"Ningbo University,The Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]},{"given":"Sihui","family":"Luo","sequence":"additional","affiliation":[{"name":"Ningbo University,The Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]},{"given":"Lijun","family":"Guo","sequence":"additional","affiliation":[{"name":"Ningbo University,The Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]},{"given":"Rong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ningbo University,The Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00524"},{"key":"ref7","article-title":"Part-dependent label noise: Towards instance-dependent label noise","author":"Xia","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref8","article-title":"Are anchor points really indispensable in label-noise learning?","author":"Xia","year":"2019","journal-title":"Neural Information Processing Systems"},{"article-title":"Estimating instance-dependent bayes-label transition matrix using a deep neural network","volume-title":"International Conference on Machine Learning (ICML)","author":"Yang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17319"},{"article-title":"Dividemix: Learning with noisy labels as semi-supervised learning","year":"2020","author":"Li","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","year":"2018","author":"Zhang","key":"ref13"},{"key":"ref14","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","author":"Han","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6950"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/354384.354443"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521352"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2004.1394263"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2011.6012139"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2018.2815998"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-75786-5_3","article-title":"Video highlight detection via deep ranking modeling","volume-title":"Pacific-Rim Symposium on Image and Video Technology","author":"Jiao"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12335"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_12"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref34","article-title":"Attention bottlenecks for multimodal fusion","author":"Nagrani","year":"2021","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6988"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref37","first-page":"300","article-title":"Learning trailer moments in full-length movies","volume-title":"ECCV","author":"Wang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299154"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref40"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651049.pdf?arnumber=10651049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:35:02Z","timestamp":1725942902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651049","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}