{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:56:20Z","timestamp":1777704980590,"version":"3.51.4"},"reference-count":11,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2024,4,18]]},"abstract":"<jats:p>Pose estimation plays a crucial role in human-centered vision applications and has advanced significantly in recent years. However, prevailing approaches use extremely complex structural designs for obtaining high scores on the benchmark dataset, hampering edge device applications. In this study, an efficient and lightweight human pose estimation problem is investigated. Enhancements are made to the context enhancement module of the U-shaped structure to improve the multi-scale local modeling capability. With a transformer structure, a lightweight transformer block was designed to enhance the local feature extraction and global modeling ability. Finally, a lightweight pose estimation network\u2014 U-shaped Hybrid Vision Transformer, UViT\u2014 was developed. The minimal network UViT-T achieved a 3.9% improvement in AP scores on the COCO validation set with fewer model parameters and computational complexity compared with the best-performing V2 version of the MobileNet series. Specifically, with an input size of 384\u00d7288, UViT-T achieves an impressive AP score of 70.2 on the COCO test-dev set, with only 1.52 M parameters and 2.32 GFLOPs. The inference speed is approximately twice that of general-purpose networks. This study provides an efficient and lightweight design idea and method for the human pose estimation task and provides theoretical support for its deployment on edge devices.<\/jats:p>","DOI":"10.3233\/jifs-231440","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T11:18:49Z","timestamp":1708427929000},"page":"8345-8359","source":"Crossref","is-referenced-by-count":0,"title":["UViT: Efficient and lightweight U-shaped hybrid vision transformer for human pose estimation"],"prefix":"10.1177","volume":"46","author":[{"given":"Biao","family":"Li","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"},{"name":"School of Mechanical and Electronic Engineering, Suzhou University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoufeng","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"},{"name":"School of Mechanical and Electronic Engineering, Suzhou University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-231440_ref1","first-page":"7444","article-title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition, 32nd AAAI Conference on Artificial Intelligence","volume":"2018","author":"Yan","year":"2018","journal-title":"AAAI"},{"key":"10.3233\/JIFS-231440_ref3","doi-asserted-by":"crossref","first-page":"4207","DOI":"10.3233\/JIFS-222985","article-title":"Myoelectric human computer interaction using CNN-LSTM neural network for dynamic hand gesture recognition","volume":"44","author":"Li","year":"2023","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.3233\/JIFS-231440_ref22","doi-asserted-by":"crossref","first-page":"107404","DOI":"10.1016\/j.patcog.2020.107404","article-title":"U2-Net: Going deeper with nested U-structure for salient object detection,","volume":"106","author":"Qin","year":"2020","journal-title":"Pattern Recognition"},{"key":"10.3233\/JIFS-231440_ref37","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.neucom.2021.12.083","article-title":"UULPN: An Ultra-lightweight Network for Human Pose Estimation Based on Unbiased Data Processing","volume":"480","author":"Wang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.3233\/JIFS-231440_ref38","doi-asserted-by":"crossref","unstructured":"Zhang S. , Qiang B. , Yang X. , Wei X. , Chen R. and Chen L. , Human Pose Estimation via an Ultra-Lightweight Pose Distillation Network, , Electronics 12 (2023).","DOI":"10.3390\/electronics12122593"},{"key":"10.3233\/JIFS-231440_ref42","doi-asserted-by":"crossref","first-page":"2375","DOI":"10.1007\/s11263-021-01465-9","article-title":"OCNet: Object Context for Semantic Segmentation,","volume":"129","author":"Yuan","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/JIFS-231440_ref44","doi-asserted-by":"crossref","first-page":"4587","DOI":"10.1109\/TII.2021.3118466","article-title":"Data-driven remanufacturability evaluation method of waste parts,","volume":"18","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.3233\/JIFS-231440_ref45","doi-asserted-by":"crossref","first-page":"5553","DOI":"10.3233\/JIFS-212061","article-title":"Human pose estimation based on parallel atrous convolution and body structure constraints","volume":"42","author":"Zhang","year":"2022","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.3233\/JIFS-231440_ref47","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","article-title":"Squeeze-and-Excitation Networks,","volume":"42","author":"Hu","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/JIFS-231440_ref48","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TMM.2021.3068576","article-title":"Spatial Pyramid Attention for Deep Convolutional Neural Networks,","volume":"23","author":"Ma","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.3233\/JIFS-231440_ref69","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully Convolutional Networks for Semantic Segmentation","volume":"39","author":"Shelhamer","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-231440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:42:35Z","timestamp":1777455755000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-231440"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,18]]},"references-count":11,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/jifs-231440","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,18]]}}}