{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:17:59Z","timestamp":1783174679909,"version":"3.54.6"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"publisher","award":["SRG\/2023\/002108"],"award-info":[{"award-number":["SRG\/2023\/002108"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"publisher","award":["ANRF\/IRG\/2024\/001321\/ENS"],"award-info":[{"award-number":["ANRF\/IRG\/2024\/001321\/ENS"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems Architecture"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.sysarc.2026.103836","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T10:32:52Z","timestamp":1778581972000},"page":"103836","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["GateAttn-ViT: Entropy-gated, attention-guided token pruning for resource-efficient Vision Transformer acceleration on FPGAs"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4229-1114","authenticated-orcid":false,"given":"Akshansh","family":"Yadav","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1979-0298","authenticated-orcid":false,"given":"Palash","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.sysarc.2026.103836_b1","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103836_b2","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103836_b3","series-title":"Linformer: Self-Attention with Linear Complexity","author":"Wang","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103836_b4","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103836_b5","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-End Object Detection with Transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103836_b6","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103836_b7","series-title":"DeepViT: Towards Deeper Vision Transformer","author":"Zhou","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103836_b8","series-title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103836_b9","series-title":"Rethinking attention with performers","author":"Choromanski","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103836_b10","doi-asserted-by":"crossref","first-page":"16344","DOI":"10.52202\/068431-1189","article-title":"FLASHATTENTION: Fast and Memory-Efficient Exact Attention with IO-Awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103836_b11","first-page":"12077","article-title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103836_b12","doi-asserted-by":"crossref","unstructured":"Q. Guo, J. Wan, S. Xu, M. Li, Y. Wang, HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline, in: Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design, 2024, pp. 1\u20139.","DOI":"10.1145\/3676536.3676681"},{"key":"10.1016\/j.sysarc.2026.103836_b13","series-title":"Multi-scale and token mergence: Make your ViT more efficient","author":"Bian","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103836_b14","series-title":"The Role of Token Pruning in Efficient Transformer Architectures","author":"Tai","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103836_b15","series-title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","author":"Zhang","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103836_b16","doi-asserted-by":"crossref","unstructured":"M. Kim, S. Gao, Y.-C. Hsu, Y. Shen, H. Jin, Token Fusion: Bridging the Gap between Token Pruning and Token Merging, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 1383\u20131392.","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"10.1016\/j.sysarc.2026.103836_b17","article-title":"RelViT: Relational Token Pruning for Vision Transformers","author":"Kang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.sysarc.2026.103836_b18","series-title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","author":"Ganjdanesh","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103836_b19","first-page":"13937","article-title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.sysarc.2026.103836_b20","doi-asserted-by":"crossref","first-page":"7682","DOI":"10.1109\/TPAMI.2024.3392941","article-title":"A Survey on Efficient Vision Transformers: Algorithms, Techniques, and Performance Benchmarking","volume":"46","author":"Papa","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.sysarc.2026.103836_b21","series-title":"2023 IEEE International Symposium on High-Performance Computer Architecture","first-page":"442","article-title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","author":"Dong","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103836_b22","series-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103836_b23","series-title":"Australasian Joint Conference on Artificial Intelligence","first-page":"28","article-title":"No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling","author":"Xu","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103836_b24","doi-asserted-by":"crossref","unstructured":"S. Wei, T. Ye, S. Zhang, Y. Tang, J. Liang, Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers, in: Proceedings of CVPR 2023, 2023.","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"10.1016\/j.sysarc.2026.103836_b25","series-title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","author":"Liang","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103836_b26","doi-asserted-by":"crossref","unstructured":"X. Xu, S. Wang, Y. Chen, Y. Zheng, Z. Wei, J. Liu, GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 86\u201395.","DOI":"10.1109\/WACV57701.2024.00016"},{"key":"10.1016\/j.sysarc.2026.103836_b27","series-title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","author":"Sun","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103836_b28","series-title":"2022 32nd International Conference on Field-Programmable Logic and Applications","first-page":"109","article-title":"Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization","author":"Li","year":"2022"},{"issue":"11","key":"10.1016\/j.sysarc.2026.103836_b29","doi-asserted-by":"crossref","first-page":"4088","DOI":"10.1109\/TCAD.2022.3197489","article-title":"ViA: A Novel Vision-Transformer Accelerator Based on FPGA","volume":"41","author":"Wang","year":"2022","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"10.1016\/j.sysarc.2026.103836_b30","series-title":"2023 IEEE International Symposium on Circuits and Systems","first-page":"1","article-title":"ViTA: A Vision Transformer Inference Accelerator for Edge Applications","author":"Nag","year":"2023"},{"issue":"1","key":"10.1016\/j.sysarc.2026.103836_b31","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1109\/TVLSI.2025.3604705","article-title":"MoE-Sched: Enabling Efficient FPGA Deployment of Mixture-of-Experts Vision Transformers via Coordinated Scheduling","volume":"34","author":"Dong","year":"2026","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"key":"10.1016\/j.sysarc.2026.103836_b32","series-title":"2024 Design, Automation & Test in Europe Conference & Exhibition","first-page":"1","article-title":"ViT-ToGo: Vision Transformer Accelerator with Grouped Token Pruning","author":"Lee","year":"2024"},{"issue":"3","key":"10.1016\/j.sysarc.2026.103836_b33","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"10.1016\/j.sysarc.2026.103836_b34","doi-asserted-by":"crossref","first-page":"8762","DOI":"10.1109\/ACCESS.2021.3049294","article-title":"Multi-head self-attention transformation networks for aspect-based sentiment analysis","volume":"9","author":"Lin","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.sysarc.2026.103836_b35","unstructured":"Y. Yu, X. Ma, J. Zhang, ViT-ToGo: Token-Grained Vision Transformer Acceleration, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 17345\u201317354."},{"key":"10.1016\/j.sysarc.2026.103836_b36","series-title":"2025 Design, Automation & Test in Europe Conference","first-page":"1","article-title":"Hybrid token selector based accelerator for vits","author":"Yadav","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103836_b37","doi-asserted-by":"crossref","unstructured":"H. Wang, B. Dedhia, N.K. Jha, Zero-TPrune: Zero-shot token pruning through leveraging of the attention graph in pre-trained transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 16070\u201316079.","DOI":"10.1109\/CVPR52733.2024.01521"},{"key":"10.1016\/j.sysarc.2026.103836_b38","series-title":"Timm: PyTorch image models","author":"Wightman","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103836_b39","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.sysarc.2026.103836_b40","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103836_b41","series-title":"PyTorch image models","author":"Wightman","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103836_b42","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3143","article-title":"Width & Depth Pruning for Vision Transformers","volume":"vol. 36","author":"Yu","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103836_b43","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.sysarc.2026.103836_b44","article-title":"Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume":"32","author":"Barbu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001542?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001542?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T13:38:18Z","timestamp":1783172298000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1383762126001542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":44,"alternative-id":["S1383762126001542"],"URL":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103836","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GateAttn-ViT: Entropy-gated, attention-guided token pruning for resource-efficient Vision Transformer acceleration on FPGAs","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems Architecture","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103836","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103836"}}