{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:40Z","timestamp":1792786900224,"version":"4.5.0"},"reference-count":101,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62406177"],"award-info":[{"award-number":["62406177"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Shandong Excellent Young Scientists Fund","award":["2024HWYQ-027"],"award-info":[{"award-number":["2024HWYQ-027"]}]},{"name":"Natural Science Foundation of Shandong Province, China","award":["ZR2023QF124"],"award-info":[{"award-number":["ZR2023QF124"]}]},{"name":"Young Scholars Program of Shandong University","id":[{"id":"https:\/\/ror.org\/0207yh398","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3724025","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T19:31:28Z","timestamp":1786735888000},"page":"15003-15020","source":"Crossref","is-referenced-by-count":0,"title":["M3R++: Masked Token Mixup and Dual Cross-Modal Masking for Zero-Shot Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3707-1761","authenticated-orcid":false,"given":"Qiangchang","family":"Wang","sequence":"first","affiliation":[{"name":"Shandong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0808-8258","authenticated-orcid":false,"given":"Yuchi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Shandong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9488-8236","authenticated-orcid":false,"given":"Rushi","family":"Lan","sequence":"additional","affiliation":[{"name":"Guilin University of Electronic Technology","place":["Guilin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8465-1294","authenticated-orcid":false,"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[{"name":"Shandong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9794-3221","authenticated-orcid":false,"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[{"name":"Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"646","article-title":"Zero-data learning of new tasks.","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"1","author":"Larochelle","year":"2008"},{"key":"ref2","first-page":"1410","article-title":"Zero-shot learning with semantic output codes","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"22","author":"Palatucci","year":"2009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref8","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Socher","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142181"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00773"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350901"},{"key":"ref16","first-page":"16622","article-title":"HSVA: Hierarchical semantic-visual adaptation for zero-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01515"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/114"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00913"},{"key":"ref20","first-page":"1","article-title":"Adaptive and generative zero-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chou","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282971"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3351439"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00859"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/217"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02230"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00113"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00746"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01456"},{"key":"ref30","first-page":"2936","article-title":"Dual progressive prototype network for generalized zero-shot learning","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"34","author":"Wang","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00961"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5923"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547889"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3325533"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01472"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612104"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref39","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"ref42","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1034"},{"key":"ref44","first-page":"1","article-title":"Co-Mixup: Saliency guided joint mixup with supermodular diversity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref46","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"issue":"8","key":"ref47","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref49","first-page":"1","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2022"},{"key":"ref50","article-title":"How to understand masked autoencoders","author":"Cao","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548173"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1691"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1039"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02145"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2081"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref63","first-page":"1298","article-title":"Data2Vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref64","article-title":"Multimodal masked autoencoders learn transferable representations","volume-title":"Proc. 1st Workshop Pre-training: Perspectives, Pitfalls, Paths Forward","author":"Geng","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0894"},{"key":"ref69","first-page":"1","article-title":"Contrastive audio-visual masked autoencoder","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref71","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02544"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01048"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00029"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00328"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2216"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3335"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref83","article-title":"Caltech-UCSD Birds 200","author":"Welinder","year":"2010"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"issue":"11","key":"ref86","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/449"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00909"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/534"},{"key":"ref90","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xu","year":"2020"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00379"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19909"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3229526"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374217"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02262"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25114"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02053-3"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02394-7"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32366"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01888"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11656262.pdf?arnumber=11656262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:15:19Z","timestamp":1791486919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11656262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":101,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3724025","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":[[2026,11]]}}}