{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T09:13:25Z","timestamp":1754558005387,"version":"3.37.3"},"reference-count":107,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0100403"],"award-info":[{"award-number":["2018AAA0100403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61876094","U1933114"],"award-info":[{"award-number":["61876094","U1933114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin, China","doi-asserted-by":"publisher","award":["20JCJQJC00020","18JCYBJC15400","18ZXZNGX00110"],"award-info":[{"award-number":["20JCJQJC00020","18JCYBJC15400","18ZXZNGX00110"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3094744","type":"journal-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T20:40:35Z","timestamp":1626122435000},"page":"6512-6527","source":"Crossref","is-referenced-by-count":9,"title":["BiSPL: Bidirectional Self-Paced Learning for Recognition From Web Data"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3067-4626","authenticated-orcid":false,"given":"Xiaoping","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0610-907X","authenticated-orcid":false,"given":"Jianlong","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0219-3443","authenticated-orcid":false,"given":"Jufeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.178"},{"key":"ref31","article-title":"Training deep neural-networks using a noise adaptation layer","author":"goldberger","year":"2017","journal-title":"Proc ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref37","first-page":"69","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"noroozi","year":"2016","journal-title":"Proc ECCV"},{"key":"ref36","first-page":"649","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref35","first-page":"21271","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref34","first-page":"9729","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref27","first-page":"273","article-title":"Learning from Web data using adversarial discriminative neural networks for fine-grained classification","author":"yang","year":"2019","journal-title":"Proc AAAI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.311"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01286"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123432"},{"key":"ref23","first-page":"4032","article-title":"Deck: Discovering event composition knowledge from Web images for zero-shot event detection and recounting in videos","author":"gan","year":"2017","journal-title":"Proc AAAI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.125"},{"key":"ref101","article-title":"Domain adaptive transfer learning with specialist models","author":"ngiam","year":"2018","journal-title":"arXiv 1811 07056"},{"key":"ref25","first-page":"849","article-title":"Webly-supervised video recognition by mutually voting for relevant Web images and Web video frames","author":"gan","year":"2016","journal-title":"Proc ECCV"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref50","first-page":"3630","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc NIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00452"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2917524"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2567393"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.05.043"},{"key":"ref53","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc NIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2903401"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"ref4","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume":"2","author":"khosla","year":"2011","journal-title":"Proc CVPR Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"article-title":"The caltech-UCSD birds-200-2011 dataset","year":"2011","author":"wah","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01312"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref7","first-page":"135","article-title":"CurriculumNet: Weakly supervised learning from large-scale Web images","author":"guo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01134"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00010"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2915591"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2965534"},{"key":"ref47","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv 1609 02907"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref41","first-page":"11804","article-title":"Removing the background by adding the background: Towards background robust self-supervised video representation learning","author":"wang","year":"2021","journal-title":"Proc CVPR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889949"},{"key":"ref43","first-page":"568","article-title":"Consensus-driven propagation in massive unlabeled data for face recognition","author":"zhan","year":"2018","journal-title":"Proc ECCV"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.146"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298916"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2016.2602231"},{"key":"ref70","article-title":"SNN: Stacked neural networks","author":"mohammadi","year":"2016","journal-title":"arXiv 1605 08512"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451560"},{"key":"ref77","first-page":"70","article-title":"Pairwise confusion for fine-grained visual classification","author":"dubey","year":"2018","journal-title":"Proc ECCV"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723400"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref79","first-page":"355","article-title":"Grassmann pooling as compact homogeneous bilinear pooling for fine-grained visual classification","author":"wei","year":"2018","journal-title":"Proc ECCV"},{"journal-title":"Advanced Engineering Mathematics","year":"1979","author":"kreyszig","key":"ref60"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref61","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc ECCV"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00571"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2631122"},{"key":"ref68","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc NIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref2","first-page":"1137","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref94","article-title":"Metric learning with adaptive density discrimination","author":"rippel","year":"2016","journal-title":"Proc ICLR"},{"key":"ref93","first-page":"420","article-title":"Learning to navigate for fine-grained classification","author":"yang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref107","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref106","first-page":"8769","article-title":"The Naturalist species classification and detection dataset","author":"van horn","year":"2018","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00534"},{"key":"ref105","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017","journal-title":"arXiv 1708 04552"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00524"},{"key":"ref103","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc ICML"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00755"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.04.005"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102963"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.11.028"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.133"},{"key":"ref11","first-page":"301","article-title":"The unreasonable effectiveness of noisy data for fine-grained recognition","author":"krause","year":"2016","journal-title":"Proc ECCV"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855449"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/2986035.2986042"},{"key":"ref17","first-page":"233","article-title":"A closer look at memorization in deep networks","author":"arpit","year":"2017","journal-title":"Proc ICML"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.68"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2961910"},{"key":"ref84","first-page":"834","article-title":"Part-based R-CNNs for fine-grained category detection","author":"zhang","year":"2014","journal-title":"Proc ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00749"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2629443"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301274"},{"key":"ref89","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","author":"sohn","year":"2016","journal-title":"Proc NIPS"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_57"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298995"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.276"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09481191.pdf?arnumber=9481191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:03Z","timestamp":1652194263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9481191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":107,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3094744","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2021]]}}}