https://lynne-zheng-linfang.github.io/publications/

1<!doctype html><html lang="en" class="no-js"><head><meta charset="utf-8"> <!-- begin SEO --><title>Publications - Linfang Zheng (郑林芳)</title><meta property="og:locale" content="en-US"><meta property="og:site_name" content="Linfang Zheng (郑林芳)"><meta property="og:title" content="Publications"><link rel="canonical" href="https://lynne-zheng-linfang.github.io/publications/"><meta property="og:url" content="https://lynne-zheng-linfang.github.io/publications/"> 

1<script type="application/ld+json"> { "@context" : "http://schema.org", "@type" : "Person", "name" : "Linfang Zheng", "url" : "https://lynne-zheng-linfang.github.io", "sameAs" : null } </script>

1 <!-- end SEO --><meta name="google-site-verification" content="LDXJGCpvVup5pPoMYLgzugPIWaYDdUoeeJlF7HQCto8" /><link href="https://lynne-zheng-linfang.github.io/feed.xml" type="application/atom+xml" rel="alternate" title="Linfang Zheng (郑林芳) Feed"> <!-- http://t.co/dKP3o1e --><meta name="HandheldFriendly" content="True"><meta name="MobileOptimized" content="320"><meta name="viewport" content="width=device-width, initial-scale=1.0"> 

1<script> document.documentElement.className = document.documentElement.className.replace(/\bno-js\b/g, '') + ' js '; </script>

1 <!-- For all browsers --><link rel="stylesheet" href="https://lynne-zheng-linfang.github.io/assets/css/main.css"><meta http-equiv="cleartype" content="on"> <!-- start custom head snippets --><link rel="apple-touch-icon" sizes="57x57" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-57x57.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="60x60" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-60x60.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="72x72" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-72x72.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="76x76" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-76x76.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="114x114" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-114x114.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="120x120" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-120x120.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="144x144" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-144x144.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="152x152" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-152x152.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="180x180" href="https://lynne-zheng-linfang.github.io/images/apple-touch-icon-180x180.png?v=M44lzPylqQ"><link rel="icon" type="image/png" href="https://lynne-zheng-linfang.github.io/images/favicon-32x32.png?v=M44lzPylqQ" sizes="32x32"><link rel="icon" type="image/png" href="https://lynne-zheng-linfang.github.io/images/android-chrome-192x192.png?v=M44lzPylqQ" sizes="192x192"><link rel="icon" type="image/png" href="https://lynne-zheng-linfang.github.io/images/favicon-96x96.png?v=M44lzPylqQ" sizes="96x96"><link rel="icon" type="image/png" href="https://lynne-zheng-linfang.github.io/images/favicon-16x16.png?v=M44lzPylqQ" sizes="16x16"><link rel="manifest" href="https://lynne-zheng-linfang.github.io/images/manifest.json?v=M44lzPylqQ"><link rel="mask-icon" href="https://lynne-zheng-linfang.github.io/images/safari-pinned-tab.svg?v=M44lzPylqQ" color="#000000"><link rel="shortcut icon" href="/images/favicon.ico?v=M44lzPylqQ"><meta name="msapplication-TileColor" content="#000000"><meta name="msapplication-TileImage" content="https://lynne-zheng-linfang.github.io/images/mstile-144x144.png?v=M44lzPylqQ"><meta name="msapplication-config" content="https://lynne-zheng-linfang.github.io/images/browserconfig.xml?v=M44lzPylqQ"><meta name="theme-color" content="#ffffff"><link rel="stylesheet" href="https://lynne-zheng-linfang.github.io/assets/css/academicons.css"/> <!-- Support for MatJax --> 

1<script src="https://cdnjs.cloudflare.com/polyfill/v3/polyfill.min.js?features=es6"></script>

1 

1<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>

1 <!-- end custom head snippets --></head><body> <!--[if lt IE 9]><div class="notice--danger align-center" style="margin: 0;">You are using an <strong>outdated</strong> browser. Please <a href="http://browsehappy.com/">upgrade your browser</a> to improve your experience.</div><![endif]--><div class="masthead"><div class="masthead__inner-wrap"><div class="masthead__menu"><nav id="site-nav" class="greedy-nav"> <button><div class="navicon"></div></button><ul class="visible-links"><li class="masthead__menu-item masthead__menu-item--lg"><a href="https://lynne-zheng-linfang.github.io/">Linfang Zheng (郑林芳)</a></li><li class="masthead__menu-item"><a href="https://lynne-zheng-linfang.github.io/publications/">Publications</a></li></ul><ul class="hidden-links hidden"></ul></nav></div></div></div><div id="main" role="main"><div class="sidebar sticky"><div itemscope itemtype="http://schema.org/Person"><div class="author__avatar"> <img src="https://lynne-zheng-linfang.github.io/images/profile.jpeg" class="author__avatar" alt="Linfang Zheng (郑林芳)"></div><div class="author__content"><h3 class="author__name">Linfang Zheng (郑林芳)</h3><p class="author__pronouns">She/Her</p><p class="author__bio">Postdoctoral Follow</p></div><div class="author__urls-wrapper"> <button class="btn btn--inverse">Follow</button><ul class="author__urls social-icons"> <!-- Font Awesome icons / Biographic information --><li class="author__desktop"><i class="fa-solid fa-location-dot icon-pad-right" aria-hidden="true"></i>China</li><li class="author__desktop"><i class="fa fa-solid fa-building-columns icon-pad-right" aria-hidden="true"></i>The University of Hong Kong</li><!-- Font Awesome and Academicons icons / Academic websites --><li><a href="https://scholar.google.com/citations?user=GeE0cQ0AAAAJ&hl=zh-CN"><i class="ai ai-google-scholar icon-pad-right"></i>Google Scholar</a></li><!-- Font Awesome icons / Repositories and software development --><li><a href="https://github.com/Lynne-Zheng-Linfang"><i class="fab fa-fw fa-github icon-pad-right" aria-hidden="true"></i>Github</a></li><!-- Font Awesome icons / Social media --></ul></div></div></div><div class="archive"><h1 class="page__title">Publications</h1><div class="wordwrap">You can also find my articles on <a href="https://scholar.google.com/citations?user=GeE0cQ0AAAAJ&amp;hl=zh-CN">my Google Scholar profile</a>.</div><div class="list__item"><article class="archive__item" itemscope="" itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://lynne-zheng-linfang.github.io/publication/2024-06-17-GeoReF" rel="permalink">GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement </a></h2><p>Published in <i>the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2024</p><p class="archive__item-excerpt" itemprop="description"><p>Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. <a href="https://lynne-zheng-linfang.github.io/georef.github.io/">Project page</a></p></p><p>Recommended citation: Linfang Zheng, Tze Ho Elden Tse, Chen Wang, Yinghan Sun, Hua Chen, Ales Leonardis, Wei Zhang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 <a href=""></a></p></article></div><div class="list__item"><article class="archive__item" itemscope="" itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://lynne-zheng-linfang.github.io/publication/2024-05-13-PlanExtraction" rel="permalink">Multi-Resolution Planar Region Extraction for Uneven Terrains </a></h2><p>Published in <i>the IEEE International Conference on Robotics and Automation (ICRA)</i>, 2024</p><p class="archive__item-excerpt" itemprop="description"><p>This paper studies the problem of extracting planar regions in uneven terrains from unordered point cloud measurements. Such a problem is critical in various robotic applications such as robotic perceptive locomotion. While existing approaches have shown promising results in effectively extracting planar regions from the environment, they often suffer from issues such as low computational efficiency or loss of resolution. To address these issues, we propose a multi-resolution planar region extraction strategy in this paper that balances the accuracy in boundaries and computational efficiency.

1</p></p><p>Recommended citation: Yinghan Sun, Linfang Zheng, Hua Chen, Wei Zhang, "Multi-Resolution Planar Region Extraction for Uneven Terrains," 2024 International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 2024 <a href=""></a></p></article></div><div class="list__item"><article class="archive__item" itemscope="" itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://lynne-zheng-linfang.github.io/publication/2023-06-17-3DGaze" rel="permalink">Where Are They Looking in the 3D Space? </a></h2><p>Published in <i>the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops</i>, 2023</p><p class="archive__item-excerpt" itemprop="description"><p>We propose a novel depth-aware joint attention target estimation framework that estimates the attention target in 3D space. Our goal is to mimic human’s ability to understand where each person is looking in their proximity. In this work, we tackle the previously unexplored problem of utilising a depth prior along with a 3D joint FOV probability map to estimate the joint attention target of people in the scene.</p></p><p>Recommended citation: Nora Horanyi, Linfang Zheng, Eunji Chong, Aleš Leonardis, Hyung Jin Chang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 2678-2687 <a href=""></a></p></article></div><div class="list__item"><article class="archive__item" itemscope="" itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://lynne-zheng-linfang.github.io/publication/2023-03-28-HSPose" rel="permalink">HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation </a></h2><p>Published in <i>the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2023</p><p class="archive__item-excerpt" itemprop="description"><p>In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC) based methods have been widely used to extract local geometric features, but they have limitations for complex shaped objects and are sensitive to noise. Moreover, the scale and translation invariant properties of 3D-GC restrict the perception of an object’s size and translation information. In this paper, we propose a simple network structure, the HS-layer, which extends 3D-GC to extract hybrid scope latent features from point cloud data for category-level object pose estimation tasks. <a href="https://lynne-zheng-linfang.github.io/hspose.github.io/">Project page</a></p></p><p>Recommended citation: Linfang Zheng, Chen Wang, Yinghan Sun, Esha Dasgupta, Hua Chen, Aleš Leonardis, Wei Zhang, Hyung Jin Chang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 17163-17173 <a href=""></a></p></article></div><div class="list__item"><article class="archive__item" itemscope="" itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://lynne-zheng-linfang.github.io/publication/2023-02-12-Trans6D" rel="permalink">Trans6D: Transformer-Based 6D Object Pose Estimation and Refinement </a></h2><p>Published in <i>the European Conference on Computer Vision (ECCV) Workshops</i>, 2023</p><p class="archive__item-excerpt" itemprop="description"><p>Estimating 6D object pose from a monocular RGB image remains challenging due to factors such as texture-less and occlusion. Although convolution neural network (CNN)-based methods have made remarkable progress, they are not efficient in capturing global dependencies and often suffer from information loss due to downsampling operations. To extract robust feature representation, we propose a Transformer-based 6D object pose estimation approach (Trans6D).</p></p><p>Recommended citation: Zhang, Z., Chen, W., Zheng, L., Leonardis, A., Chang, H.J. (2023). Trans6D: Transformer-Based 6D Object Pose Estimation and Refinement. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13808. Springer, Cham. https://doi.org/10.1007/978-3-031-25085-9_7 <a href=""></a></p></article></div><div class="list__item"><article class="archive__item" itemscope="" itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://lynne-zheng-linfang.github.io/publication/2022-07-01-TPAE" rel="permalink">TP-AE: Temporally Primed 6D Object Pose Tracking with Auto-Encoders </a></h2><p>Published in <i>the IEEE International Conference on Robotics and Automation (ICRA)</i>, 2022</p><p class="archive__item-excerpt" itemprop="description"><p>Fast and accurate tracking of an object’s motion is one of the key functionalities of a robotic system for achieving reliable interaction with the environment. This paper focuses on the instance-level 6D pose tracking problem with a symmetric and textureless object under occlusion. We propose a Temporally Primed 6D pose tracking framework with Auto-Encoders (TP-AE) to tackle the pose tracking problem. <a href="https://lynne-zheng-linfang.github.io/TP-AE.github.io/">Project Page</a></p></p><p>Recommended citation: L. Zheng et al., "TP-AE: Temporally Primed 6D Object Pose Tracking with Auto-Encoders," 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, PA, USA, 2022, pp. 10616-10623, doi: 10.1109/ICRA46639.2022.9811890. <a href=""></a></p></article></div><div class="list__item"><article class="archive__item" itemscope="" itemtype="http://schema.org/CreativeWork"><h2 class="archive__item-title" itemprop="headline"> <a href="https://lynne-zheng-linfang.github.io/publication/2020-03-01-QLearning" rel="permalink">Optimal Control Inspired Q-Learning for Switched Linear Systems </a></h2><p>Published in <i>the American Control Conference (ACC)</i>, 2020</p><p class="archive__item-excerpt" itemprop="description"><p>This paper studies Q-learning for quadratic regulation problem of switched linear systems. Inspired by the analytical results from classical model-based optimal control, a structured Q-learning algorithm is developed.</p></p><p>

1Recommended citation: H. Chen, L. Zheng and W. Zhang, "Optimal Control Inspired Q-Learning for Switched Linear Systems," 2020 American Control Conference (ACC), Denver, CO, USA, 2020, pp. 4003-4010, doi: 10.23919/ACC45564.2020.9147818. <a href=""></a></p></article></div></div></div><div class="page__footer"><footer> <!-- start custom footer snippets --> <a href="/sitemap/">Sitemap</a> <!-- end custom footer snippets --><div class="page__footer-follow"><ul class="social-icons"><li><strong>Follow:</strong></li><li><a href="http://github.com/Lynne-Zheng-Linfang"><i class="fab fa-github" aria-hidden="true"></i> GitHub</a></li><li><a href="https://lynne-zheng-linfang.github.io/feed.xml"><i class="fa fa-fw fa-rss-square" aria-hidden="true"></i> Feed</a></li></ul></div><div class="page__footer-copyright">&copy; 2026 Linfang Zheng. Powered by <a href="http://jekyllrb.com" rel="nofollow">Jekyll</a> &amp; <a href="https://github.com/academicpages/academicpages.github.io">AcademicPages</a>, a fork of <a href="https://mademistakes.com/work/minimal-mistakes-jekyll-theme/" rel="nofollow">Minimal Mistakes</a>.</div></footer></div>

1<script src="https://lynne-zheng-linfang.github.io/assets/js/main.min.js"></script>

1 

1<script> (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); ga('create', '', 'auto'); ga('send', 'pageview'); </script>

1</body></html>