Xionghu Zhong

Dr. Xionghu Zhong


Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
15 November 2021 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
CXCheng Xue
Cheng Xue
XZXionghu Zhong
Xionghu Zhong
MCMinjie Cai
Minjie Cai
HCHao Chen
Hao Chen
WWWenwu Wang
Wenwu Wang
This work aims to temporally localize events that are both audible and visible in video. Previous methods mainly focused on temporal modeling of events with simple fusion of audio and visual features. In natural scenes, a video records not only the events of interest but also ambient acoustic noise and visual background, resulting in redundant information in the raw audio and visual features. Thus, direct fusion of the two features often causes false localization of the events. In this paper, we propose a co-attention model to exploit the spatial and semantic correlations between the audio and visual features, which helps guide the extraction of discriminative features for better event localization. Our assumption is that in an audio-visual event, shared semantic information between audio and visual features exists and can be extracted by attention learning. Specifically, the proposed co-attention model is composed of a co-spatial attention module and a co-semantic attention module that are used to model the spatial and semantic correlations, respectively. The proposed co-attention model can be applied to various event localization tasks, such as cross-modality localization and multimodal event localization. Experiments on the public audio-visual event (AVE) dataset demonstrate that the proposed method achieves state-of-the-art performance by learning spatial and semantic co-attention.

11 March 2014 in IEEE Sensors Journal
Verified
Journal Article
Closed access
XZXionghu Zhong
Xionghu Zhong
APA. B. Premkumar
A. B. Premkumar
HWHaiyan Wang
Haiyan Wang
This paper considers the problem of tracking multiple acoustic sources in 3-D space using a distributed acoustic vector sensor array. Unlike the existing two-stage localization approach, which estimates the direction of arrival of the source at each sensor first and then triangulate a 3-D position, a particle filtering approach is developed to directly fuse the signals collected from distributed sensors. To enhance the tracking performance and constrain the computational complexity, an information filter is developed to approximate the optimal importance sampling. Since the position state of the source is linear with the velocity state, a Rao-Blackwellization step is employed to marginalize out the velocity component. In addition, the posterior Cramér-Rao bound is developed to provide a lower performance bound for the distributed tracking system. Both the numerical study and simulations show that the proposed tracking approach significantly outperforms the two-stage localization approaches for 3-D position estimation.

28 September 2024 in Sensors
Verified
Journal Article
Open access
PDF file
JLJuan Luo
Juan Luo
CWChongxiao Wang
Chongxiao Wang
JYJielong Yang
Jielong Yang
XZXionghu Zhong
Xionghu Zhong
The efficient detection of leakages in water distribution networks (WDNs) is crucial to ensuring municipal water supply safety and improving urban operations. Traditionally, machine learning methods such as Convolutional Neural Networks (CNNs) and Autoencoders (AEs) have been used for leakage detection. However, these methods heavily rely on local pressure information and often fail to capture long-term dependencies in pressure series. In this paper, we propose a transformer-based model for detecting leakages in WDNs. The transformer incorporates an attention mechanism to learn data distributions and account for correlations between historical pressure data and data from the same time on different days, thereby emphasizing long-term dependencies in pressure series. Additionally, we apply pressure data normalization across each leakage scenario and concatenate position embeddings with pressure data in the transformer model to avoid feature misleading. The performance of the proposed method is evaluated by using detection accuracy and F1-score. The experimental studies conducted on simulated pressure datasets from three different WDNs demonstrate that the transformer-based model significantly outperforms traditional CNN methods.

24 June 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
MCMinjie Cai
Minjie Cai
JKJianaresi Kezierbieke
Jianaresi Kezierbieke
XZXionghu Zhong
Xionghu Zhong
HCHao Chen
Hao Chen
This work tackles the cross-domain object detection problem which aims to generalize a pre-trained object detector to different domains (driving scenes) without labels. An uncertainty-aware and class-balanced domain adaptation method is proposed based on two motivations: 1) estimation and exploitation of model uncertainty in a new domain is critical for reliable domain adaptation; and 2) in domain adaptation the distribution alignment of two domains as well as the maintaining of category discriminability are both important. In particular, we compose a Bayesian CNN-based framework for uncertainty estimation in object detection. We propose an algorithm for generating uncertainty-aware pseudo-labels, which are then used in uncertainty-guided self-training and category-aware feature alignment. We further devise a scheme with class-balanced memory banks to address the long-tail distribution problem in category-aware feature alignment. Experiments on multiple cross-domain object detection benchmarks show that our proposed method achieves state-of-the-art performance.

18 May 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ZLZhaogeng Liu
Zhaogeng Liu
JYJielong Yang
Jielong Yang
XZXionghu Zhong
Xionghu Zhong
WWWenwu Wang
Wenwu Wang
HCHechang Chen
Hechang Chen
YCYi Chang
Yi Chang
Graph neural networks (GNNs) have achieved great success in many fields due to their powerful capabilities of processing graph-structured data. However, most GNNs can only be applied to scenarios where graphs are known, but real-world data are often noisy or even do not have available graph structures. Recently, graph learning has attracted increasing attention in dealing with these problems. In this article, we develop a novel approach to improving the robustness of the GNNs, called composite GNN. Different from existing methods, our method uses composite graphs (C-graphs) to characterize both sample and feature relations. The C-graph is a unified graph that unifies these two kinds of relations, where edges between samples represent sample similarities, and each sample has a tree-based feature graph to model feature importance and combination preference. By jointly learning multiaspect C-graphs and neural network parameters, our method improves the performance of semisupervised node classification and ensures robustness. We conduct a series of experiments to evaluate the performance of our method and the variants of our method that only learn sample relations or feature relations. Extensive experimental results on nine benchmark datasets demonstrate that our proposed method achieves the best performance on almost all the datasets and is robust to feature noises.

16 February 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
JYJielong Yang
Jielong Yang
RDRui Ding
Rui Ding
JCJianyu Chen
Jianyu Chen
XZXionghu Zhong
Xionghu Zhong
HZHuarong Zhao
Huarong Zhao
Linbo XieLinbo Xie
Linbo Xie
Graph adversarial attacks can be classified as either white-box or black-box attacks. White-box attackers typically exhibit better performance because they can exploit the known structure of victim models. However, in practical settings, most attackers generate perturbations under black-box conditions, where the victim model is unknown. A fundamental question is how to leverage a white-box attacker to attack a black-box model. Some current black-box attack approaches employ white-box techniques to attack a surrogate model, resulting in satisfactory outcomes. Nonetheless, such white-box attackers must be meticulously designed and lack theoretical assurances for attack effectiveness. In this paper, we propose a novel framework that utilizes simple white-box techniques to conduct black-box attacks and provides the lower bound for attack performance. Specifically, we first employ a more comprehensive GCN technique named BiasGCN to approximate the victim model, and subsequently, use a simple white-box approach to attack the approximate model. We provide a generalization guarantee for our BiasGCN and employ it to obtain the lower bound on attack performance. Our method is evaluated on various datasets, and the experimental results indicate that our approach surpasses recently proposed baselines.