{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:32Z","timestamp":1763190812212,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227769","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["HSViT: Horizontally Scalable Vision Transformer"],"prefix":"10.1109","author":[{"given":"Chenhao","family":"Xu","sequence":"first","affiliation":[{"name":"Victoria University,ISILC,Melbourne,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang-Tsun","family":"Li","sequence":"additional","affiliation":[{"name":"Deakin University,School of IT,Geelong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee Peng","family":"Lim","sequence":"additional","affiliation":[{"name":"Swinburne University of Technology,Department of Computing Technologies,Melbourne,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Douglas","family":"Creighton","sequence":"additional","affiliation":[{"name":"Deakin University,IISRI,Geelong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01312-0"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref2"},{"key":"ref3","first-page":"12 116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref7","first-page":"12 934","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00874"},{"article-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"International Conference on Learning Representations","author":"Mehta","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref16","first-page":"16 079","article-title":"Cape: Encoding relative positions with continuous augmented positional embeddings","volume":"34","author":"Likhomanenko","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3418527"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3377454"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00216"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2023.100595"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref24"},{"journal-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"Xiao","key":"ref25"},{"key":"ref26","article-title":"Tiny imagenet challenge","author":"Wu","year":"2017","journal-title":"Technical report"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref33","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"article-title":"Mobilevitv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features","year":"2022","author":"Wadekar","key":"ref34"},{"key":"ref35","first-page":"5785","article-title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Vasu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"article-title":"Escaping the big data paradigm with compact transformers","year":"2021","author":"Hassani","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084806"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155269"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227769.pdf?arnumber=11227769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:11:05Z","timestamp":1763190665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227769","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}