{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:13:42Z","timestamp":1768281222255,"version":"3.49.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2022XKRC015"],"award-info":[{"award-number":["2022XKRC015"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National NSF of China","award":["62372033"],"award-info":[{"award-number":["62372033"]}]},{"name":"Natural Science Foundation of Beijing, China","award":["L252025"],"award-info":[{"award-number":["L252025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3621246","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:40:04Z","timestamp":1760463604000},"page":"1873-1887","source":"Crossref","is-referenced-by-count":0,"title":["A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models"],"prefix":"10.1109","volume":"48","author":[{"given":"Weixin","family":"Ye","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9837-9615","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4398-8867","authenticated-orcid":false,"given":"Yahui","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1573-5643","authenticated-orcid":false,"given":"Yue","family":"Song","sequence":"additional","affiliation":[{"name":"Caltech, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9790-1504","authenticated-orcid":false,"given":"Bin","family":"Ren","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Bi","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2239-283X","authenticated-orcid":false,"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia, Modena, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6597-7248","authenticated-orcid":false,"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3294606"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.01.007"},{"key":"ref3","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref4","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. Assoc. Comput. Linguistics","author":"Devlin","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","first-page":"611","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","first-page":"894","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref12","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"issue":"140","key":"ref13","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tom","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref19","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref20","first-page":"2245","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref22","first-page":"1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref24","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.555"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00445"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00981"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01952"},{"key":"ref29","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref35","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref36","first-page":"14745","article-title":"TransGAN: Two pure transformers can make one strong GAN, and that can scale up","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref41","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.266"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref48","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref49","article-title":"Efficient training of visual transformers with small datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref51","article-title":"iDLG: Improved deep leakage from gradients","author":"Zhao","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00978"},{"key":"ref54","first-page":"16937","article-title":"Inverting gradients\u2013how easy is it to break privacy in federated learning?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Geiping","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.305"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/259380.259405"},{"key":"ref58","first-page":"114","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Gao"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00919"},{"key":"ref60","first-page":"16433","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"issue":"4","key":"ref61","first-page":"467","article-title":"Class-based N-gram models of natural language","volume":"18","author":"Peter","year":"1992","journal-title":"Comput. Linguistics"},{"key":"ref62","first-page":"1","article-title":"N-gram-based text categorization","volume-title":"Proc. Proc. 43 rd Annu. Symp. Document Anal. Inf. Retrieval","author":"Cavnar"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref64","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref67","first-page":"2866","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref68","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2016"},{"key":"ref69","article-title":"Bridging language and items for retrieval and recommendation","author":"Hou","year":"2024"},{"key":"ref70","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. Assoc. Comput.: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref72","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1009"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.733"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11202736.pdf?arnumber=11202736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:43Z","timestamp":1768255243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11202736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":84,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3621246","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":[[2026,2]]}}}