{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T10:20:49Z","timestamp":1774261249036,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019180","name":"HORIZON EUROPE European Research Council","doi-asserted-by":"publisher","award":["101061548"],"award-info":[{"award-number":["101061548"]}],"id":[{"id":"10.13039\/100019180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3329952","type":"journal-article","created":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T18:03:59Z","timestamp":1698948239000},"page":"123433-123444","source":"Crossref","is-referenced-by-count":16,"title":["Multi-Manifold Attention for Vision Transformers"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7391-6875","authenticated-orcid":false,"given":"Dimitrios","family":"Konstantinidis","sequence":"first","affiliation":[{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4664-2626","authenticated-orcid":false,"given":"Ilias","family":"Papastratis","sequence":"additional","affiliation":[{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1584-7047","authenticated-orcid":false,"given":"Kosmas","family":"Dimitropoulos","sequence":"additional","affiliation":[{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3814-6710","authenticated-orcid":false,"given":"Petros","family":"Daras","sequence":"additional","affiliation":[{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01934122"},{"key":"ref2","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref4","article-title":"Escaping the big data paradigm with compact transformers","author":"Hassani","year":"2021","journal-title":"arXiv:2104.05704"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref12","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021","journal-title":"arXiv:2103.11886"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref14","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref15","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref17","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chu"},{"key":"ref18","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref19","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. ICLR","author":"Choromanski"},{"key":"ref20","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. ICLR","author":"Kitaev"},{"key":"ref21","article-title":"Couplformer: Rethinking vision transformer with coupling attention map","author":"Lan","year":"2021","journal-title":"arXiv:2112.05425"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01098"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3341806"},{"key":"ref26","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref28","first-page":"1","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref29","first-page":"10635","article-title":"Non-Euclidean universal approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kratsios"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2729660"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01231"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803806"},{"key":"ref33","article-title":"Collaborative representation for SPD matrices with application to image-set classification","author":"Chu","year":"2022","journal-title":"arXiv:2201.08962"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01451"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00772"},{"key":"ref36","article-title":"Deep efficient continuous manifold learning for time series modeling","author":"Jeong","year":"2021","journal-title":"arXiv:2112.03379"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044176"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0185110"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2631719"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553163"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IST.2018.8577085"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2869680"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108335"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01235"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3011717"},{"key":"ref46","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021","journal-title":"arXiv:2102.10882"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","article-title":"Covariance of motion and appearance featuresfor spatio temporal recognition tasks","author":"Bhattacharya","year":"2016","journal-title":"arXiv:1606.05355"},{"key":"ref49","article-title":"Riemannian metric learning for symmetric positive definite matrices","author":"Vemulapalli","year":"2015","journal-title":"arXiv:1501.02393"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.387"},{"key":"ref51","article-title":"Grassmannian learning: Embedding geometry awareness in shallow and deep learning","author":"Zhang","year":"2018","journal-title":"arXiv:1808.02229"},{"key":"ref52","first-page":"1","article-title":"Orthogonalizing convolutional layers with the Cayley transform","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Trockman"},{"key":"ref53","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"ref54","first-page":"3","volume-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref57","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref59","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref64","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"issue":"11","key":"ref65","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10305583.pdf?arnumber=10305583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T12:07:39Z","timestamp":1709381259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10305583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3329952","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}