{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:43:52Z","timestamp":1775695432207,"version":"3.50.1"},"reference-count":200,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2022YFC3301004"],"award-info":[{"award-number":["2022YFC3301004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2022YFF0712300"],"award-info":[{"award-number":["2022YFF0712300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tcsvt.2023.3284405","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T17:28:39Z","timestamp":1686331719000},"page":"2-16","source":"Crossref","is-referenced-by-count":12,"title":["The Image Data and Backbone in Weakly Supervised Fine-Grained Visual Categorization: A Revisit and Further Thinking"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7756-8233","authenticated-orcid":false,"given":"Shuo","family":"Ye","sequence":"first","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4863-5681","authenticated-orcid":false,"given":"Qinmu","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0607-1777","authenticated-orcid":false,"given":"Xinge","family":"You","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892802"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2408566"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref5","volume-title":"Cassava Leaf Disease Classification","author":"ErnestMwebaze","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940446"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3076684"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108257"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2754648"},{"key":"ref10","article-title":"Oriented feature alignment for fine-grained object recognition in high-resolution satellite imagery","author":"Ming","year":"2021","journal-title":"arXiv:2110.06628"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108552"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3020079"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2834480"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref22","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"Branson","year":"2014","journal-title":"arXiv:1406.2952"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2521428"},{"key":"ref24","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv:1312.4400"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.130"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102790"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869721"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2903036"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2966644"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.127"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00749"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/145"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/87"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2932058"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref44","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop FGVC","volume":"2","author":"Khosla"},{"key":"ref45","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_36"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref48","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.259"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.66"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.647"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_35"},{"key":"ref60","article-title":"RPC: A large-scale retail product checkout dataset","author":"Wei","year":"2019","journal-title":"arXiv:1901.07249"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01269"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00458"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2021.114135"},{"key":"ref65","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref66","first-page":"24529","article-title":"ZIN: When and how to learn invariance without environment partition?","volume-title":"Proc. NIPS","author":"Yong"},{"issue":"1","key":"ref67","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref68","first-page":"11842","article-title":"Delving into deep imbalanced regression","volume-title":"Proc. ICML","author":"Yang"},{"key":"ref69","first-page":"2532","article-title":"Large-scale long-tailed recognition in an open world","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Liu"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00638"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.276"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351156"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2599102"},{"key":"ref80","article-title":"Mask-CNN: Localizing parts and selecting descriptors for fine-grained image recognition","author":"Wei","year":"2016","journal-title":"arXiv:1605.06878"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.136"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/103"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993960"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2751960"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090274"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2607345"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.688"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_22"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074313"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3204337"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.022"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224477"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08250-4"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723400"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2813971"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_22"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_38"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2977457"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.325"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.63"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.229"},{"key":"ref115","first-page":"1","article-title":"Maximum-entropy fine grained classification","volume-title":"Proc. NIPS","volume":"31","author":"Dubey"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2852721"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2895651"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref119","first-page":"1","article-title":"Birds of a feather flock together-local learning of mid-level representations for fine-grained recognition","volume-title":"Proc. ECCV Workshop","volume":"2","author":"Freytag"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.15"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.131"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.126"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301271"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477700"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366567"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.007"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3134156"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.311"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301273"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref133","first-page":"1","article-title":"Active bias: Training more accurate neural networks by emphasizing high variance samples","volume-title":"Proc. NIPS","volume":"30","author":"Chang"},{"key":"ref134","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. ICML","author":"Ren"},{"key":"ref135","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. ICML","author":"Song"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3055024"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref138","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref142","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref143","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref145","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raghu"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref147","article-title":"Feature fusion vision transformer for fine-grained visual categorization","author":"Wang","year":"2021","journal-title":"arXiv:2107.02341"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref149","article-title":"A free lunch from ViT: Adaptive attention multi-scale fusion transformer for fine-grained visual recognition","author":"Zhang","year":"2021","journal-title":"arXiv:2110.01240"},{"key":"ref150","article-title":"R2-trans: Fine-grained visual categorization with redundancy reduction","author":"Wang","year":"2022","journal-title":"arXiv:2204.10095"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.037"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3114622"},{"key":"ref153","article-title":"A novel plug-in module for fine-grained visual classification","author":"Chou","year":"2022","journal-title":"arXiv:2202.03822"},{"key":"ref154","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume-title":"Proc. NIPS","volume":"34","author":"Li"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978115"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3124135"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2996736"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00977"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027603"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069835"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00066"},{"key":"ref163","article-title":"Re-rank coarse classification with local region enhanced features for fine-grained image recognition","author":"Yang","year":"2021","journal-title":"arXiv:2102.09875"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117064"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126668"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3135477"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534004"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3213563"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3238548"},{"key":"ref171","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. NIPS","volume":"28","author":"Jaderberg"},{"key":"ref172","first-page":"15316","article-title":"Augmented shortcuts for vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tang"},{"key":"ref173","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Naseer"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"ref175","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019","journal-title":"arXiv:1907.02893"},{"key":"ref176","first-page":"145","article-title":"Invariant risk minimization games","volume-title":"Proc. ICML","author":"Ahuja"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3032958"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001510"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043128"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-021-00265-1"},{"key":"ref181","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP49819.2020.9301763"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16255"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00325"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3112768"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2019.2906120"},{"key":"ref191","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00526"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00886"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3065693"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015084"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3179020"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01067"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2932976"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2968509"},{"key":"ref200","article-title":"CDLT: A dataset with concept drift and long-tailed distribution for fine-grained visual categorization","author":"Ye","year":"2023","journal-title":"arXiv:2306.02346"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10382161\/10147290.pdf?arnumber=10147290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T20:15:31Z","timestamp":1736799331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10147290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":200,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3284405","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}