{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T09:44:29Z","timestamp":1756460669395,"version":"3.40.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project, China,","doi-asserted-by":"publisher","award":["242102241064"],"award-info":[{"award-number":["242102241064"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3563890","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T17:06:45Z","timestamp":1745514405000},"page":"74739-74749","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Large Railway Vision Models for Efficient In-Context Learning"],"prefix":"10.1109","volume":"13","author":[{"given":"Xuemei","family":"Zhan","sequence":"first","affiliation":[{"name":"Zhengzhou Railway Vocational and Technical College, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubo","family":"Wu","sequence":"additional","affiliation":[{"name":"Agreeya, Fremont, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7746-4639","authenticated-orcid":false,"given":"Hua","family":"Ma","sequence":"additional","affiliation":[{"name":"Zhengzhou Railway Vocational and Technical College, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01960"},{"article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref4","article-title":"Personalize segment anything model with one shot","author":"Zhang","year":"2023","journal-title":"arXiv:2305.03048"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"article-title":"NASVit: Neural architecture search for efficient vision transformers with gradient conflict aware supernet training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gong","key":"ref8"},{"article-title":"Post-training quantization for vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","key":"ref9"},{"key":"ref10","article-title":"Attention map guided transformer pruning for edge device","author":"Mao","year":"2023","journal-title":"arXiv:2304.01452"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref12","article-title":"Deep retinex decomposition for low-light enhancement","author":"Wei","year":"2018","journal-title":"arXiv:1808.04560"},{"key":"ref13","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2022","journal-title":"arXiv:2206.02680"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"article-title":"Fast vision transformers with HiLo attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00182"},{"key":"ref20","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref22","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref28","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"article-title":"Visual prompting via image inpainting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bar","key":"ref29"},{"key":"ref30","article-title":"Smarttrim: Adaptive tokens and attention pruning for efficient vision-language models","author":"Wang","year":"2024","journal-title":"arXiv:2305.15033"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref33","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Riquelme"},{"key":"ref34","first-page":"12934","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20176"},{"key":"ref37","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref38","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2022","journal-title":"arXiv:2109.10852"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref40","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref41","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hua"},{"key":"ref42","first-page":"711","article-title":"Data movement is all you need: A case study on optimizing transformers","volume-title":"Proc. Mach. Learn. and Syst.","author":"Ivanov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/DSD53832.2021.00074"},{"key":"ref44","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"arXiv:1912.01703"},{"key":"ref47","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"arXiv:1711.05101"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.186"},{"key":"ref54","article-title":"High quality monocular depth estimation via transfer learning","author":"Alhashim","year":"2019","journal-title":"arXiv:1812.11941"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416065"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref60","article-title":"Hrformer: High-resolution transformer for dense prediction","author":"Yuan","year":"2021","journal-title":"arXiv:2110.09408"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00275"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_30"},{"key":"ref64","first-page":"26295","article-title":"UVIM: A unified modeling approach for vision with learned guiding codes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kolesnikov"},{"key":"ref65","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022","journal-title":"arXiv:2206.08916"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10975287.pdf?arnumber=10975287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:27:21Z","timestamp":1746592041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10975287\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3563890","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}