Wenqiang Xu

Wenqiang Xu

Auto-generated profile, based on publicly available information

Wenqiang Xu

School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
5 January 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LLLiu Liu
Liu Liu
HXHan Xue
Han Xue
WXWenqiang Xu
Wenqiang Xu
HFHaoyuan Fu
Haoyuan Fu
CLCewu Lu
Cewu Lu
Human life is populated with articulated objects. Current Category-level Articulation Pose Estimation (CAPE) methods are studied under the single-instance setting with a fixed kinematic structure for each category. Considering these limitations, we aim to study the problem of estimating part-level 6D pose for multiple articulated objects with unknown kinematic structures in a single RGB-D image, and reform this problem setting for real-world environments and suggest a CAPE-Real (CAPER) task setting. This setting allows varied kinematic structures within a semantic category, and multiple instances to co-exist in an observation of real world. To support this task, we build an articulated model repository ReArt-48 and present an efficient dataset generation pipeline, which contains Fast Articulated Object Modeling (FAOM) and Semi-Authentic MixEd Reality Technique (SAMERT). Accompanying the pipeline, we build a large-scale mixed reality dataset ReArtMix and a real world dataset ReArtVal. Accompanying the CAPER problem and the dataset, we propose an effective framework that exploits RGB-D input to estimate part-level pose for multiple instances in a single forward pass. In our method, we introduce object detection from RGB-D input to handle the multi-instance problem and segment each instance into several parts. To address the unknown kinematic structure issue, we propose an Articulation Parsing Network to analyze the structure of detected instance, and also build a Pair Articulation Pose Estimation module to estimate per-part 6D pose as well as joint property from connected part pairs. Extensive experiments demonstrate that the proposed method can achieve good performance on CAPER, CAPE and instance-level Robot Arm pose estimation problems. We believe it could serve as a strong baseline for future research on the CAPER task. The datasets and codes in our work will be made publicly available.

4 November 2024 in JAMA Network Open
Verified
Journal Article
Open access
PDF file
QHQiang Hua
Qiang Hua
LWLu Wang
Lu Wang
KHKongliang He
Kongliang He
JSJinmei Sun
Jinmei Sun
WXWenqiang Xu
Wenqiang Xu
GJGong-Jun Ji
Gong-Jun Ji
Importance: Auditory verbal hallucinations (AVH) are a common symptom of schizophrenia, increasing the patient’s risks of suicide and violence. Repetitive transcranial magnetic stimulation (rTMS) is a potential treatment for AVH.Objective: To investigate the effect of imaging-navigated rTMS on AVH in patients with schizophrenia.Design, Setting, and Participants: This 6-week, double-blind, sham-controlled, randomized clinical trial was performed at the Anhui Mental Health Center, Hefei, China, from September 1, 2016, to August 31, 2021. Participants included 66 patients with AVH and schizophrenia. Data were analyzed from May 1, 2022, to March 31, 2023.Interventions: Participants were randomly assigned 1:1 to either imaging-navigated active or sham rTMS over the left temporoparietal junction for 2 weeks.Main Outcomes and Measures: The primary outcome measured improvements in AVH from baseline to week 2 and week 6 using the Auditory Hallucination Rating Scale (AHRS) scores. In addition, the TMS-induced electric field strength was used to estimate improvements in AVH as a secondary outcome.Results: A total of 62 participants (33 women [53%]; mean [SD] age, 27.4 [9.2] years) completed the 2-week treatments. Of these, 32 were randomized to the active rTMS group (18 women [56%]; mean [SD] age, 26.9 [9.2] years) and 30 to the sham treatment group (15 women [50%]; mean [SD] age, 27.8 [9.4] years). In the intention-to-treat analyses, patients receiving active rTMS showed a significantly greater reduction in AHRS scores compared with those receiving sham treatment at week 2 (difference, 5.96 [95% CI, 3.42-8.50]; t = 4.61; P < .001; Cohen d, 1.17 [95% CI, 0.62-1.71]). These clinical effects were sustained at week 6. Additionally, a stronger TMS-induced electric field within a predefined AVH brain network was associated with greater reductions in AHRS scores (B = 3.12; t = 3.58; P = .002). No serious adverse event was observed.Conclusions and Relevance: The findings of this randomized clinical trial suggest that imaging-navigated rTMS may effectively and safely alleviate AVH in patients with schizophrenia. Findings also suggest that the electric field strength in the individualized AVH network is a vital parameter for optimizing the efficacy of the rTMS protocol.Trial Registration: ClinicalTrials.gov Identifier: NCT02863094

22 March 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LYLixin Yang
Lixin Yang
XZXinyu Zhan
Xinyu Zhan
KLKailin Li
Kailin Li
WXWenqiang Xu
Wenqiang Xu
JZJunming Zhang
Junming Zhang
CLCewu Lu
Cewu Lu
Estimating and synthesizing the hand's manipulation of objects is central to understanding human behaviour. To accurately model the interaction between the hand and object (referred to as the “hand-object”), we must not only focus on the pose of the hand and object, but also consider the contact between them. This contact provides valuable information for generating semantically and physically plausible grasps. In this paper, we propose an explicit contact representation called Contact Potential Field (CPF). In CPF, we model the contact between a pair of hand-object vertices as a spring-mass system. This system encodes the distance of the pair, as well as a likelihood of that contact being stable. Therefore, the system of multiple extended and compressed springs forms an elastic potential field with minimal energy at the optimal grasp position. We apply CPF to two relevant tasks, namely, hand-object pose estimation and grasping pose generation. Extensive experiments on the two challenging tasks and three commonly used datasets have demonstrated that our method can achieve state-of-the-art in several reconstruction metrics, allowing us to produce more physically plausible hand-object poses even when the ground-truth exhibits severe interpenetration or disjointedness. Our model and source codes are made publicly available at https://github.com/lixiny/CPF.

22 January 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
WDWenxin Du
Wenxin Du
WXWenqiang Xu
Wenqiang Xu
JRJieji Ren
Jieji Ren
ZYZhenjun Yu
Zhenjun Yu
CLCewu Lu
Cewu Lu
Tactile perception stands as a critical sensory modality for human interaction with the environment. Among various tactile sensor techniques, optical sensor-based approaches have gained traction, notably for producing high-resolution tactile images. This letter explores gel elastomer deformation simulation through a physics-based approach. While previous works in this direction usually adopt the explicit material point method (MPM), which has certain limitations in force simulation and rendering, we adopt the finite element method (FEM) and address the challenges in mesh penetration and element inversion with incremental potential contact (IPC) method. As a result, we present a simulator named TacIPC, which can ensure numerically stable simulations while accommodating direct rendering and friction modeling. To evaluate TacIPC, we conduct four tasks: pseudo-image quality assessment, marker displacement prediction, slip-induced rotation prediction, and deformed geometry estimation. These tasks show its superior efficacy in reducing the sim-to-real gap. Our method can also seamlessly integrate with existing simulators.

27 December 2023 in Neural Networks
Verified
Journal Article
Open access
YFYu Fang
Yu Fang
XZXuehe Zhang
Xuehe Zhang
WXWenqiang Xu
Wenqiang Xu
GLGangfeng Liu
Gangfeng Liu
JZJie Zhao
Jie Zhao
Inspired by visual-tactile cross-modal bidirectional mapping of the human brain, this paper introduces a novel approach to bidirectional mapping between visual and tactile data, an area not fully explored in the predominantly unidirectional existing studies. First, we adopt separate Variational AutoEncoder (VAE) models for visual and tactile data. Furthermore, we introduce a conditional flow model built on the VAE latent feature space, enabling cross-modal bidirectional mapping between visual and tactile data using one model. The experimental results show that our method achieves excellent performance in terms of the similarity between the generated data and the original data (Structural Similarity Index (SSIM) of visual data: 0.58, SSIM of tactile data: 0.80), the classification accuracy on generated data (visual data: 91.60%, tactile data: 88.05%), and the zero-shot classification accuracy between generated data and language (visual data: 44.49%, tactile data: 45.03%). To the best of our knowledge, the method proposed in this paper is the first one to utilize a single model to achieve bidirectional mapping between visual and tactile data. Our model and code will be made public after the acceptance of the paper.