{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:56:27Z","timestamp":1784904987679,"version":"3.55.0"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62471448"],"award-info":[{"award-number":["62471448"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2024YQ004"],"award-info":[{"award-number":["ZR2024YQ004"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010029","name":"TaiShan Scholars Youth Expert Program of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202312109"],"award-info":[{"award-number":["tsqn202312109"]}],"id":[{"id":"10.13039\/501100010029","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3671661","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:40:22Z","timestamp":1773348022000},"page":"2555-2569","source":"Crossref","is-referenced-by-count":1,"title":["LearnMat: Semantic-Aware Self-Supervision Fine-Grained Visual Recognition"],"prefix":"10.1109","volume":"35","author":[{"given":"Shuaiheng","family":"Li","sequence":"first","affiliation":[{"name":"Department of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-6156","authenticated-orcid":false,"given":"Qing","family":"Cai","sequence":"additional","affiliation":[{"name":"Innovation School of Artificial Intelligence, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2478-4722","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangyang","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Systems and Computing, University of New South Wales, Canberra, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7012-2087","authenticated-orcid":false,"given":"Junyu","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3584-795X","authenticated-orcid":false,"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5027-5286","authenticated-orcid":false,"given":"David","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref2","article-title":"The iNaturalist species classification and detection dataset","author":"Van Horn","year":"2017","journal-title":"arXiv:1707.06642"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01259-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/rs13040747"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108257"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00890"},{"key":"ref7","article-title":"Fine-grained ImageNet classification in the wild","author":"Lymperaiou","year":"2023","journal-title":"arXiv:2303.02400"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/srep41545"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3055617"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2921876"},{"key":"ref11","first-page":"2570","article-title":"Delving into multimodal prompting for fine-grained visual classification","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Xin"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00670"},{"key":"ref13","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3244340"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19930"},{"key":"ref19","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2021","journal-title":"arXiv:2105.04906"},{"key":"ref20","first-page":"15509","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Bachman"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110426"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00537"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i4.37241"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0001195"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10770-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2933510"},{"key":"ref30","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387317"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13133300"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000700"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1364\/OE.18.011607"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00728"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01096"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3469962"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_26"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-021-06592-8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01434"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.192"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122772"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093373"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.03.035"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00407"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.13"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00147"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3579032"},{"key":"ref53","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref54","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0430-4"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref61","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NIPS","author":"Caron"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17312"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01556"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/607"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_7"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01091"},{"key":"ref68","article-title":"Align yourself: Self-supervised pre-training for fine-grained recognition via saliency alignment","author":"Di Wu","year":"2021","journal-title":"arXiv:2106.15788"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3370731"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3567834"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref72","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2021"},{"key":"ref73","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv:2111.07783"},{"key":"ref74","article-title":"MaPLe: Multi-modal prompt learning","author":"Khattak","year":"2022","journal-title":"arXiv:2210.03117"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.420"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01369"},{"key":"ref79","article-title":"FILS: Self-supervised video feature prediction in semantic language space","author":"Ahmadian","year":"2024","journal-title":"arXiv:2406.03447"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230743"},{"issue":"9","key":"ref81","first-page":"9112","article-title":"SGTC: Semantic-guided triplet co-training for sparsely annotated semi-supervised medical image segmentation","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"39","author":"Ke"},{"key":"ref82","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref85","article-title":"The caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref87","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240523"},{"issue":"1","key":"ref91","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":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref95","article-title":"Exploring localization for self-supervised fine-grained contrastive learning","author":"Wu","year":"2021","journal-title":"arXiv:2106.15788"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01405"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_28"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586118"},{"key":"ref101","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","author":"Qu","year":"2025","journal-title":"arXiv:2502.06501"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3629609"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11433510.pdf?arnumber=11433510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:11:51Z","timestamp":1774296711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3671661","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}