{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:40:06Z","timestamp":1730281206249,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"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":[[2024,8,15]]},"DOI":"10.1109\/mapr63514.2024.10660940","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:23:27Z","timestamp":1725992607000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["ICViT: Integrated Framework for Complexity Reduction in Vision Transformer"],"prefix":"10.1109","author":[{"given":"Tien","family":"Dang","sequence":"first","affiliation":[{"name":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"}]},{"given":"Khanh-Duy","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}]},{"given":"Khang","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}]}],"member":"263","reference":[{"key":"ref1","first-page":"20014","article-title":"Xcit: Cross-covariance image transformers","volume":"34","author":"Ali","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_3"},{"article-title":"Language Models are Few-Shot Learners","year":"2020","author":"Brown","key":"ref3"},{"article-title":"Efficientvit: Enhanced linear attention for high-resolution low-computation visual recognition","year":"2022","author":"Cai","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"article-title":"Conditional positional encodings for vision transformers","volume-title":"ICLR 2023","author":"Chu","key":"ref6"},{"key":"ref7","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Chu","year":"2021"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref8"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"article-title":"Transformer in transformer","year":"2021","author":"Han","key":"ref11"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref12"},{"key":"ref13","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","volume-title":"International Conference on Machine Learning","author":"Katharopoulos"},{"author":"Kitaev","key":"ref14","article-title":"Reformer: The efficient transformer. In International Conference on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00259"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342025"},{"article-title":"Ecoformer: Energy-saving attention with linear complexity","year":"2022","author":"Liu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref19"},{"key":"ref20","first-page":"32","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Touvron"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"article-title":"Attention is all you need","year":"2017","author":"Vaswani","key":"ref22"},{"article-title":"Linformer: Self-attention with linear complexity","year":"2020","author":"Wang","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"article-title":"Castling-vit: Compressing self-attention via switching towards linear-angular attention during vision transformer inference","year":"2022","author":"You","key":"ref27"},{"key":"ref28","first-page":"558","article-title":"Tokens-totoken vit: Training vision transformers from scratch on imagenet","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Yuan"}],"event":{"name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","start":{"date-parts":[[2024,8,15]]},"location":"Da Nang, Vietnam","end":{"date-parts":[[2024,8,16]]}},"container-title":["2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10660665\/10660652\/10660940.pdf?arnumber=10660940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:59:40Z","timestamp":1726041580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10660940\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,15]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/mapr63514.2024.10660940","relation":{},"subject":[],"published":{"date-parts":[[2024,8,15]]}}}