Author name cluster

Zhonghua Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

EAAI Journal 2025 Journal Article

Fixed-time neural network composite learning control for uncertain nonlinear systems

Zhonghua Wu
Zhikuan Zou
Xiangwei Bu
Jianjun Zhang
Kuncheng Ma

A novel fixed-time neural network composite learning control (FNNCLC) scheme is proposed for nonlinear strict-feedback systems with unknown dynamics. The neural network (NN) is employed to handle system uncertainty. By utilizing tracking errors and prediction errors to update NN weights, accurate network learning is achieved under a weaker excitation condition termed interval excitation (IE) condition, instead of the typically required strict persistent excitation (PE) condition. Moreover, for the first time, a high order term and first order term of the prediction error are introduced to design composite learning adaptive laws, achieving the convergence of NN weights within fixed time. Additionally, a smooth fixed-time (FXT) dynamic surface control scheme is constructed without potential singularity problems, which mitigates complexity explosion by avoiding fractional power terms and complex switching strategies when formulating the control law. The stability of the proposed control scheme is analyzed by using Lyapunov technique. Simulation results demonstrate the effectiveness of the proposed controller.

Details DOI

AAAI Conference 2025 Conference Paper

IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter

Xiaojing Zhong
Zhonghua Wu
Xiaofeng Yang
Guosheng Lin
Qingyao Wu

Given a pair of images depicting a person and a garment separately, image-based 3D virtual try-on methods aim to reconstruct a 3D human model that realistically portrays the person wearing the desired garment. In this paper, we present IPVTON, a novel image-based 3D virtual try-on framework. IPVTON employs score distillation sampling with image prompts to optimize a hybrid 3D human representation, integrating target garment features into diffusion priors through an image prompt adapter. To avoid interference with non-target areas, we leverage mask-guided image prompt embeddings to focus the image features on the try-on regions. Moreover, we impose geometric constraints on the 3D model with a pseudo silhouette generated by ControlNet, ensuring that the clothed 3D human model retains the shape of the source identity while accurately wearing the target garments. Extensive qualitative and quantitative experiments demonstrate that IPVTON outperforms previous methods in image-based 3D virtual try-on tasks, excelling in both geometry and texture.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Modeling Continuous Motion for 3D Point Cloud Object Tracking

Zhipeng Luo
Gongjie Zhang
Changqing Zhou
Zhonghua Wu
Qingyi Tao
Lewei Lu
Shijian Lu

The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling within only two successive frames, thereby overlooking the long-range continuous motion property of objects in 3D space. To address this issue, this paper presents a novel approach that views each tracklet as a continuous stream: at each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank, enabling efficient exploitation of sequential information. To achieve effective cross-frame message passing, a hybrid attention mechanism is designed to account for both long-range relation modeling and local geometric feature extraction. Furthermore, to enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed, which uses ground truth tracklets to augment training sequences and promote discrimination against false positives in a contrastive manner. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art method by significant margins on multiple benchmarks.

PDF Details DOI

EAAI Journal 2023 Journal Article

CVT on-line error measurement hybrid-driven by domain knowledge and Stacking Model

Jingping Wang
Ying Shi
Rui Zhang
Zhonghua Wu
Hao Ye
Shenwei Li

The performance of Capacitive Voltage Transformer (CVT) degrades over time, making measurement error monitoring a research hotspot in the field of smart grid. At present, these are several challenges such as complex data features, a lack of criteria for selecting optimal measurement models, and low precision. CVT measurement errors can be classified into ideal error and additional one. The former is typically evaluated via mutual information and redundancy within the topology-level transformer group. Considering that a single model cannot process the time series, strong randomness and nonlinearity of the additional error, the Stacking model is selected. Based on the principle of heterogeneity and high-quality, correlation coefficient and feature contribution degree, Random Forest, eXtreme Gradient Boosting, Ridge Regression, K Nearest Neighbors, Support Vector Regression, and Long Short-Term Memory are chosen as base learners through correlation and feature contribution analysis; while extra-trees with strong generalization and robustness is chosen as the meta learner. To improve the measurement precision, the attention-like mechanism is used to scale time and accuracy weights. Finally, according to the power domain knowledge, a linear superposition model is developed to fuse the ideal and additional errors, and thus realize online error measurement for CVTs. The experimental results indicate that the improved Stacking model outperforms mainstream measurement models by an average reduction of 59. 47%, and 52. 58% in the root mean squared error and the mean absolute error with the best R 2 closest to 1. It not only effectively improves the accuracy but also meets speed requirement for online error measurement.

Details DOI

NeurIPS Conference 2023 Conference Paper

Towards Robust and Expressive Whole-body Human Pose and Shape Estimation

Hui En Pang
Zhongang Cai
Lei Yang
Qingyi Tao
Zhonghua Wu
Tianwei Zhang
Ziwei Liu

Whole-body pose and shape estimation aims to jointly predict different behaviors (e. g. , pose, hand gesture, facial expression) of the entire human body from a monocular image. Existing methods often exhibit suboptimal performance due to the complexity of in-the-wild scenarios. We argue that the prediction accuracy of these models is significantly affected by the quality of the bounding box, e. g. , scale, alignment. The natural discrepancy between the ideal bounding box annotations and model detection results is particularly detrimental to the performance of whole-body pose and shape estimation. In this paper, we propose a novel framework to enhance the robustness of whole-body pose and shape estimation. Our framework incorporates three new modules to address the above challenges from three perspectives: (1) a Localization Module enhances the model's awareness of the subject's location and semantics within the image space; (2) a Contrastive Feature Extraction Module encourages the model to be invariant to robust augmentations by incorporating a contrastive loss and positive samples; (3) a Pixel Alignment Module ensures the reprojected mesh from the predicted camera and body model parameters are more accurate and pixel-aligned. We perform comprehensive experiments to demonstrate the effectiveness of our proposed framework on body, hands, face and whole-body benchmarks.

PDF Details