{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:36:44Z","timestamp":1779295004817,"version":"3.51.4"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Education Tier 2 grant, NUS, Singapore","award":["T2EP20224-0028"],"award-info":[{"award-number":["T2EP20224-0028"]}]},{"name":"Ministry of Education Tier 2 grant, NUS, Singapore","award":["24-1250-P0001"],"award-info":[{"award-number":["24-1250-P0001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tpami.2025.3584902","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T17:38:58Z","timestamp":1752687538000},"page":"9187-9200","source":"Crossref","is-referenced-by-count":2,"title":["Pro-NeXt: An All-in-One Unified Model for General Fine-Grained Visual Recognition"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7174-9276","authenticated-orcid":false,"given":"Junde","family":"Wu","sequence":"first","affiliation":[{"name":"University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7028-9968","authenticated-orcid":false,"given":"Jiayuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0881-5891","authenticated-orcid":false,"given":"Min","family":"Xu","sequence":"additional","affiliation":[{"name":"MBZUAI, Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-3877","authenticated-orcid":false,"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Comparing deep neural networks against humans: Object recognition when the signal gets weaker","author":"Geirhos","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0876-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref10","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref11","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref13","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jaderberg"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11223"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.688"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00585"},{"key":"ref26","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref27","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00702"},{"key":"ref29","article-title":"Deep learning scaling is predictable, empirically","author":"Hestness","year":"2017"},{"key":"ref30","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref31","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref35","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref36","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01167"},{"key":"ref38","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/166"},{"key":"ref42","first-page":"980","article-title":"Global filter networks for image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"ref46","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sitzmann"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref48","article-title":"Network in network","author":"Lin","year":"2013"},{"key":"ref49","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"issue":"1","key":"ref51","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization","volume":"2","author":"Khosla"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76550-z"},{"key":"ref53","article-title":"Refuge2 challenge: Treasure for multi-domain learning in glaucoma assessment","author":"Fang","year":"2022"},{"key":"ref54","article-title":"Large-scale classification of fine-art paintings: Learning the right metric on the right feature","author":"Saleh","year":"2015"},{"key":"ref55","article-title":"The iMet collection 2019 challenge dataset","author":"Zhang","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.263"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00548"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP49819.2020.9301763"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837012"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2022.100233"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/138"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00063"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-33-4673-4_55"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.2.021208"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph182111086"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102313"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.02.010"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16434-7_65"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2021.03.006"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463636"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-019-00963-0"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2907986"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123405"},{"key":"ref80","first-page":"327","article-title":"Recognizing art style automatically in painting with deep learning","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Lecoutre"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350977"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref84","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref85","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"ref87","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.01683","article-title":"TransNeXt: Robust foveal visual perception for vision transformers","author":"Shi","year":"2024"},{"key":"ref88","article-title":"DAT++ : Spatially dynamic vision transformer with deformable attention","author":"Xia","year":"2023"},{"key":"ref89","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.01386","article-title":"EfficientViT: Memory efficient vision transformer with cascaded group attention","author":"Liu","year":"2023"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_17"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01386"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3145238"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19918"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_36"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00216"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3023152"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506058"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"ref102","article-title":"Recurseed and edgepredictmix: Single-stage learning is sufficient for weakly-supervised semantic segmentation","author":"Jo","year":"2022"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_71"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102938"},{"key":"ref105","article-title":"Cbam on FGVC discussion","year":"2010"},{"key":"ref106","article-title":"Are we done with imagenet?","author":"Beyer","year":"2020"},{"key":"ref107","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/2509315.2509318"},{"key":"ref109","article-title":"ExpNet: A unified network for expert-level classification","author":"Wu","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11163533\/11081804.pdf?arnumber=11081804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:11:29Z","timestamp":1758028289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11081804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":108,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3584902","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}