{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:22Z","timestamp":1778051542199,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00043","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"360-370","source":"Crossref","is-referenced-by-count":0,"title":["A Universal Self-Attention Enhancement for Bridging Low-bit Quantization and Vision Transformers"],"prefix":"10.1109","author":[{"given":"Jiahe","family":"Qian","sequence":"first","affiliation":[{"name":"C2DL, Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peisong","family":"Wang","sequence":"additional","affiliation":[{"name":"C2DL, Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyang","family":"Zhuge","sequence":"additional","affiliation":[{"name":"C2DL, Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghao","family":"Hu","sequence":"additional","affiliation":[{"name":"C2DL, Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"C2DL, Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume":"32","author":"Banner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","article-title":"Pact: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018"},{"key":"ref5","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref6","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume":"28","author":"Courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Patch n\u2019pack: Navit, a vision transformer for any aspect ratio and resolution","volume":"36","author":"Dehghani","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547826"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref11","article-title":"Learned step size quantization","author":"Esser","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01781"},{"key":"ref13","article-title":"Hardware-oriented approximation of convolutional neural networks","author":"Gysel","year":"2016"},{"key":"ref14","first-page":"12633","article-title":"Global context vision transformers","volume-title":"International Conference on Machine Learning","author":"Hatamizadeh"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_46"},{"key":"ref17","article-title":"Istr: End-to-end instance segmentation with transformers","author":"Hu","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11660"},{"key":"ref19","article-title":"Quantization variation: A new perspective on training transformers with low-bit precision","author":"Huang","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref20","article-title":"Binarized neural networks","volume":"29","author":"Hubara","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref23","first-page":"0","article-title":"Low-bit quantization of neural networks for efficient inference","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops","author":"Kravchik"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3403844"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1350"},{"key":"ref27","article-title":"Uniformerv2: Spatiotemporal learning by arming image vits with video uniformer","author":"Li","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2496"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"3","key":"ref33","article-title":"Fq-vit: Fully quantized vision transformer without retraining","volume":"2","author":"Lin","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00156"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01946"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00460"},{"key":"ref41","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6900"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159369"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref45","first-page":"11875","article-title":"Hawq-v3: Dyadic neural network quantization","volume-title":"International Conference on Machine Learning","author":"Yao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00561"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126779"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref51","article-title":"Cagevit: Convolutional activation guided efficient vision transformer","author":"Zheng","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref53","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492411.pdf?arnumber=11492411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:10Z","timestamp":1778048230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00043","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}