{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:41:04Z","timestamp":1774528864455,"version":"3.50.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"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":[[2023,2]]},"DOI":"10.1109\/hpca56546.2023.10071081","type":"proceedings-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T17:42:55Z","timestamp":1679679775000},"page":"415-428","source":"Crossref","is-referenced-by-count":53,"title":["ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention"],"prefix":"10.1109","author":[{"given":"Jyotikrishna","family":"Dass","sequence":"first","affiliation":[{"name":"Rice University,Houston,TX"}]},{"given":"Shang","family":"Wu","sequence":"additional","affiliation":[{"name":"Rice University,Houston,TX"}]},{"given":"Huihong","family":"Shi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA"}]},{"given":"Chaojian","family":"Li","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA"}]},{"given":"Zhifan","family":"Ye","sequence":"additional","affiliation":[{"name":"Rice University,Houston,TX"}]},{"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing"}]},{"given":"Yingyan","family":"Lin","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Synopsys design compiler"},{"key":"ref2","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref3","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref4","article-title":"Efficientvit: Enhanced linear attention for high-resolution low-computation visual recognition","author":"Cai","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","article-title":"Scatterbrain: Unifying sparse and low-rank attention","volume-title":"Advances in Neural Information Processing Systems","author":"Chen","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00624"},{"key":"ref9","first-page":"19 974","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref11","article-title":"Rethinking attention with performers","volume-title":"International Conference on Learning Representations","author":"Choromanski"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1223"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1361"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref17","article-title":"Visual correspondence hallucination","volume-title":"International Conference on Learning Representations","author":"Germain"},{"key":"ref18","article-title":"NASVit: Neural architecture search for efficient vision transformers with gradient conflict aware supernet training","volume-title":"International Conference on Learning Representations","author":"Gong"},{"key":"ref19","article-title":"Pixel 3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref24","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","volume-title":"International Conference on Machine Learning","author":"Katharopoulos"},{"key":"ref25","article-title":"Reformer: The efficient transformer","volume-title":"International Conference on Learning Representations","author":"Kitaev"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","first-page":"28 092","article-title":"Post-training quantization for vision transformer","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Liu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref30","article-title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"ref31","article-title":"NVIDIA Jetson TX2"},{"key":"ref32","article-title":"GeForce RTX 2080 TI Graphics Card \u2014 NVIDIA","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref34","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530504"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00357"},{"key":"ref37","article-title":"Quadtree attention for vision transformers","volume-title":"International Conference on Learning Representations","author":"Tang"},{"key":"ref38","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","volume":"139","author":"Touvron"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref41","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref43","article-title":"Pytorch image models","author":"Wightman","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref45","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref47","article-title":"Unified visual transformer compression","author":"Yu","year":"2022"},{"key":"ref48","first-page":"17 283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","article-title":"Explicit sparse transformer: Concentrated attention through explicit selection","author":"Zhao","year":"2019"},{"key":"ref50","first-page":"arXiv","article-title":"Visual transformer pruning","author":"Zhu","year":"2021"},{"key":"ref51","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"event":{"name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2023,2,25]]},"end":{"date-parts":[[2023,3,1]]}},"container-title":["2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10070856\/10070923\/10071081.pdf?arnumber=10071081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:22:41Z","timestamp":1707830561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10071081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/hpca56546.2023.10071081","relation":{},"subject":[],"published":{"date-parts":[[2023,2]]}}}