Xingyu Li

Xingyu Li

Auto-generated profile, based on publicly available information

Xingyu Li

University of Alberta

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 February 2015 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
XLXingyu Li
Xingyu Li
KPKonstantinos Plataniotis
Konstantinos Plataniotis
Goal: In digital histopathology, tasks of segmentation and disease diagnosis are achieved by quantitative analysis of image content. However, color variation in image samples makes it challenging to produce reliable results. This paper introduces a complete normalization scheme to address the problem of color variation in histopathology images jointly caused by inconsistent biopsy staining and nonstandard imaging condition. Method : Different from existing normalization methods that either address partial cause of color variation or lump them together, our method identifies causes of color variation based on a microscopic imaging model and addresses inconsistency in biopsy imaging and staining by an illuminant normalization module and a spectral normalization module, respectively. In evaluation, we use two public datasets that are representative of histopathology images commonly received in clinics to examine the proposed method from the aspects of robustness to system settings, performance consistency against achromatic pixels, and normalization effectiveness in terms of histological information preservation. Results: As the saturation-weighted statistics proposed in this study generates stable and reliable color cues for stain normalization, our scheme is robust to system parameters and insensitive to image content and achromatic colors. Conclusion: Extensive experimentation suggests that our approach outperforms state-of-the-art normalization methods as the proposed method is the only approach that succeeds to preserve histological information after normalization. Significance: The proposed color normalization solution would be useful to mitigate effects of color variation in pathology images on subsequent quantitative analysis.

6 November 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
PSPaniz Sedighi
Paniz Sedighi
XLXingyu Li
Xingyu Li
Mahdi TavakoliMahdi Tavakoli
Mahdi Tavakoli
In the field of human-robot interaction, surface electromyography (sEMG) provides a valuable tool for measuring active muscular effort. While numerous studies have investigated real-time control of upper extremity exoskeletons based on user intention and task-specific movements, the prediction of body joint positions based on EMG features has remained largely unexplored. In this letter, we address this gap by proposing a novel approach that leverages Convolutional Neural Networks and Long-Short-Term Memory (CNN-LSTM) models to generate exoskeleton joint trajectories. Our methodology involves collecting data from three channels of EMG and three degrees-of-freedom (DoF) joint angles and enables us to position control a pneumatic cable-driven upper-limb exoskeleton, thereby assisting users in various tasks. Through extensive experimentation, our intention-based model demonstrates robust performance across different speeds and is capable of detecting variations in payload and electrode placement. The empirical results yielded from our study underscore the efficacy of our approach, particularly in reducing the EMG levels of the user during different tasks by providing exoskeleton assistance as needed.

11 March 2019 in IEEE Access
Verified
Journal Article
Open access
XLXingyu Li
Xingyu Li
Marko RadulovicMarko Radulovic
Marko Radulovic
KKKsenija Kanjer
Ksenija Kanjer
KPKonstantinos Plataniotis
Konstantinos Plataniotis
Accurate diagnosis of breast cancer in histopathology images is challenging due to the heterogeneity of cancer cell growth as well as of a variety of benign breast tissue proliferative lesions. In this paper, we propose a practical and self-interpretable invasive cancer diagnosis solution. With minimum annotation information, the proposed method mines contrast patterns between normal and malignant images in weaksupervised manner and generates a probability map of abnormalities to verify its reasoning. Particularly, a fully convolutional autoencoder is used to learn the dominant structural patterns among normal image patches. Patches that do not share the characteristics of this normal population are detected and analyzed by one-class support vector machine and 1-layer neural network.We apply the proposed method to a public breast cancer image set. Our results, in consultation with a senior pathologist, demonstrate that the proposed method outperforms existing methods. The obtained probability map could benefit the pathology practice by providing visualized verification data and potentially leads to a better understanding of data-driven diagnosis solutions.

14 August 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XZXiaohan Zhang
Xiaohan Zhang
XLXingyu Li
Xingyu Li
WSWaqas Sultani
Waqas Sultani
CCChen Chen
Chen Chen
SWSafwan Wshah
Safwan Wshah
Cross-View Geo-Localization (CVGL) estimates the location of a ground image by matching it to a geo-tagged aerial image in a database. Recent works achieve outstanding progress on CVGL benchmarks. However, existing methods still suffer from poor performance in cross-area evaluation, in which the training and testing data are captured from completely distinct areas. We attribute this deficiency to the lack of ability to extract the geometric layout of visual features and models’ overfitting to low-level details. Our preliminary work (Zhang et al. 2022) introduced a Geometric Layout Extractor (GLE) to capture the geometric layout from input features. However, the previous GLE does not fully exploit information in the input feature. In this work, we propose GeoDTR+ with an enhanced GLE module that better models the correlations among visual features. To fully explore the LS techniques from our preliminary work, we further propose Contrastive Hard Samples Generation (CHSG) to facilitate model training. Extensive experiments show that GeoDTR+ achieves state-of-the-art (SOTA) results in cross-area evaluation on CVUSA (Workman et al. 2015), CVACT (Liu and Li, 2019), and VIGOR (Zhu et al. 2021) by a large margin (16.44%, 22.71%, and 13.66% without polar transformation) while keeping the same-area performance comparable to existing SOTA. Moreover, we provide detailed analyses of GeoDTR+.

16 October 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
SLShuangzhi Li
Shuangzhi Li
ZWZhijie Wang
Zhijie Wang
FJFelix Juefei-Xu
Felix Juefei-Xu
Qing GuoQing Guo
Qing Guo
XLXingyu Li
Xingyu Li
LMLei Ma
Lei Ma
Object detection through LiDAR-based point cloud has recently been important in autonomous driving. Although achieving high accuracy on public benchmarks, the state-of-the-art detectors may still go wrong and cause a heavy loss due to the widespread corruptions in the real world like rain, snow, sensor noise, etc . Nevertheless, there is a lack of a large-scale dataset covering diverse scenes and realistic corruption types with different severities to develop practical and robust point cloud detectors, which is challenging due to the heavy collection costs. To alleviate the challenge and start the first step for robust point cloud detection, we propose the physical-aware simulation methods to generate degraded point clouds under different real-world common corruptions. Then, for the first attempt, we construct a benchmark based on the physical-aware common corruptions for point cloud detectors, which contains a total of 1,122,150 examples covering 7,481 scenes, 25 common corruption types, and 6 severities. With such a novel benchmark, we conduct extensive empirical studies on 12 state-of-the-art detectors that contain 6 different detection frameworks. Thus we get several insight observations revealing the vulnerabilities of the detectors and indicating the enhancement directions. Moreover, we further study the effectiveness of existing robustness enhancement methods based on data augmentation, data denoising, test-time adaptation. The benchmark can potentially be a new platform for evaluating point cloud detectors, opening a door for developing novel robustness enhancement methods.

16 May 2014 in Physical Review A
Verified
Journal Article
Closed access
SZSong bin Zhang
Song bin Zhang
XLXing Yu Li
Xing Yu Li
JWJian Guo Wang
Jian Guo Wang
YQYi Zhi Qu
Yi Zhi Qu
XCXiangjun Chen
Xiangjun Chen
A multicenter distorted-wave (MCDW) method for fast-electron-impact single ionization of a molecular system in the coplanar-asymmetric kinematics is developed. Plane waves are used to describe the fast incoming and outgoing electrons and the multicenter nature of the molecule is considered by describing the slow ejected electron with the multicenter distorted wave, which is solved from the anisotropic multicenter potential between the ejected electron and the ionic molecule. The MCDW method improves the conventional molecular distorted-wave methods, whose distorted wave is solved from the spherically averaged isotropic potential. The application to the water molecule shows reasonable agreement with the available experimental data.