arXiv subjects

Yu Fu

Publications and source records attributed to Yu Fu.

At least 109 records · Page 6Linked to original sources

arXiv2022

HDNet: Hierarchical Dynamic Network for Gait Recognition using Millimeter-Wave Radar

Gait recognition is widely used in diversified practical applications. Currently, the most prevalent approach is to recognize human gait from RGB images, owing to the progress of computer vision technologies. Nevertheless, the perception capability of RGB cameras deteriorates in rough circumstances, and visual surveillance may cause privacy invasion. Due to the robustness and non-invasive feature of millimeter wave (mmWave) radar, radar-based gait recognition has attracted increasing attention in recent years. In this research, we propose a Hierarchical Dynamic Network (HDNet) for gait recognition using mmWave radar. In order to explore more dynamic information, we propose point flow as a novel point clouds descriptor. We also devise a dynamic frame sampling module to promote the efficiency of computation without deteriorating performance noticeably. To prove the superiority of our methods, we perform extensive experiments on two public mmWave radar-based gait recognition datasets, and the results demonstrate that our model is superior to existing state-of-the-art methods.

cs.CV↗

arXiv2022

Scene Graph Modification as Incremental Structure Expanding

A scene graph is a semantic representation that expresses the objects, attributes, and relationships between objects in a scene. Scene graphs play an important role in many cross modality tasks, as they are able to capture the interactions between images and texts. In this paper, we focus on scene graph modification (SGM), where the system is required to learn how to update an existing scene graph based on a natural language query. Unlike previous approaches that rebuilt the entire scene graph, we frame SGM as a graph expansion task by introducing the incremental structure expanding (ISE). ISE constructs the target graph by incrementally expanding the source graph without changing the unmodified structure. Based on ISE, we further propose a model that iterates between nodes prediction and edges prediction, inferring more accurate and harmonious expansion decisions progressively. In addition, we construct a challenging dataset that contains more complicated queries and larger scene graphs than existing datasets. Experiments on four benchmarks demonstrate the effectiveness of our approach, which surpasses the previous state-of-the-art model by large margins.

cs.CV↗

arXiv2022

Deep Decomposition Network for Image Processing: A Case Study for Visible and Infrared Image Fusion

Image decomposition is a crucial subject in the field of image processing. It can extract salient features from the source image. We propose a new image decomposition method based on convolutional neural network. This method can be applied to many image processing tasks. In this paper, we apply the image decomposition network to the image fusion task. We input infrared image and visible light image and decompose them into three high-frequency feature images and a low-frequency feature image respectively. The two sets of feature images are fused using a specific fusion strategy to obtain fusion feature images. Finally, the feature images are reconstructed to obtain the fused image. Compared with the state-of-the-art fusion methods, this method has achieved better performance in both subjective and objective evaluation.

cs.CV↗

arXiv2022

PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion

The Transformer architecture has witnessed a rapid development in recent years, outperforming the CNN architectures in many computer vision tasks, as exemplified by the Vision Transformers (ViT) for image classification. However, existing visual transformer models aim to extract semantic information for high-level tasks, such as classification and detection.These methods ignore the importance of the spatial resolution of the input image, thus sacrificing the local correlation information of neighboring pixels. In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues.Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations. In addition, we construct a Pyramid Transformer to effectively extract the non-local information from the entire image. After obtaining a set of multi-scale, multi-dimensional, and multi-angle features of the original image, we design the image reconstruction network to ensure that the features can be reconstructed into the original input. To validate the effectiveness, we apply the proposed Patch Pyramid Transformer to image fusion tasks. The experimental results demonstrate its superior performance, compared to the state-of-the-art fusion approaches, achieving the best results on several evaluation indicators. Thanks to the underlying representational capacity of the PPT network, it can directly be applied to different image fusion tasks without redesigning or retraining the network.

cs.CV↗

arXiv2022

Thermalization of weakly coupled non-Abelian plasmas at next-to-leading order

We employ the QCD kinetic theory, including next-to-leading(NLO) order corrections in coupling constant, to study the evolution of weakly coupled non-Abelian plasmas towards thermal equilibrium. For two characteristic far-from-equilibrium systems with either under- or over-occupied initial conditions, the NLO corrections remain well under control for a wide range of couplings, and the overall effect of NLO corrections is a reduction in the time required for thermalization.

hep-ph↗

arXiv2022

LDoS attack detection method based on traffic time-frequency characteristics

For the traditional denial-of-service attack detection methods have complex algorithms and high computational overhead, which are difficult to meet the demand of online detection; and the experimental environment is mostly a simulation platform, which is difficult to deploy in real network environment, we propose a real network environment-oriented LDoS attack detection method based on the time-frequency characteristics of traffic data. All the traffic data flowing through the Web server is obtained through the acquisition storage system, and the detection data set is constructed using pre-processing; the simple features of the flow fragments are used as input, and the deep neural network is used to learn the time-frequency domain features of normal traffic features and generate reconstructed sequences, and the LDoS attack is discriminated based on the differences between the reconstructed sequences and the input data in the time-frequency domain. The experimental results show that the proposed method can accurately detect the attack features in the flow fragments in a very short time and achieve high detection accuracy for complex and diverse LDoS attacks; since only the statistical features of the packets are used, there is no need to parse the packet data, which can be adapted to different network environments.

cs.CR↗

arXiv2022

OTFPF: Optimal Transport-Based Feature Pyramid Fusion Network for Brain Age Estimation with 3D Overlapped ConvNeXt

Chronological age of healthy brain is able to be predicted using deep neural networks from T1-weighted magnetic resonance images (T1 MRIs), and the predicted brain age could serve as an effective biomarker for detecting aging-related diseases or disorders. In this paper, we propose an end-to-end neural network architecture, referred to as optimal transport based feature pyramid fusion (OTFPF) network, for the brain age estimation with T1 MRIs. The OTFPF consists of three types of modules: Optimal Transport based Feature Pyramid Fusion (OTFPF) module, 3D overlapped ConvNeXt (3D OL-ConvNeXt) module and fusion module. These modules strengthen the OTFPF network's understanding of each brain's semi-multimodal and multi-level feature pyramid information, and significantly improve its estimation performances. Comparing with recent state-of-the-art models, the proposed OTFPF converges faster and performs better. The experiments with 11,728 MRIs aged 3-97 years show that OTFPF network could provide accurate brain age estimation, yielding mean absolute error (MAE) of 2.097, Pearson's correlation coefficient (PCC) of 0.993 and Spearman's rank correlation coefficient (SRCC) of 0.989, between the estimated and chronological ages. Widespread quantitative experiments and ablation experiments demonstrate the superiority and rationality of OTFPF network. The codes and implement details will be released on GitHub: https://github.com/ZJU-Brain/OTFPF after final decision.

cs.CV↗

arXiv2022

Spectrum-Energy-Economy Efficiency Trade-off of Wireless Communication Systems with Separated Indoor/Outdoor Scenarios for 5G and B5G

In this paper, we consider a heterogeneous 5G cellular architecture that separates the outdoor and indoor scenarios and in particular study the trade-off between the spectrum efficiency (SE), energy efficiency (EE), economy efficiency (ECE). Mathematical expressions for the system capacity, EE, SE, and ECE respectively are derived using a proposed realistic power consumption model. The comparison of system performance in terms of SE, EE, and ECE, results in the observation that the proposed network architecture, which separates the outdoor and indoor scenarios, offers a promising solution for future communication systems that have strict requirements on the data rate and efficiency.

eess.SP↗

arXiv2022

Network Traffic Anomaly Detection Method Based on Multi scale Residual Feature

To address the problem that traditional network traffic anomaly detection algorithms do not suffi-ciently mine potential features in long time domain, an anomaly detection method based on mul-ti-scale residual features of network traffic is proposed. The original traffic is divided into subse-quences of different time spans using sliding windows, and each subsequence is decomposed and reconstructed into data sequences of different levels using wavelet transform technique; the stacked autoencoder (SAE) constructs similar feature space using normal network traffic, and gen-erates reconstructed error vector using the difference between reconstructed samples and input samples in the similar feature space; the multi-path residual group is used to learn reconstructed error The traffic classification is completed by a lightweight classifier. The experimental results show that the detection performance of the proposed method for anomalous network traffic is sig-nificantly improved compared with traditional methods; it confirms that the longer time span and more S transformation scales have positive effects on discovering potential diversity information in the original network traffic.

cs.NI↗

arXiv2022

Asymmetric transverse momentum broadening in an inhomogeneous medium

Gradient jet tomography in high-energy heavy-ion collisions utilizes the asymmetric transverse momentum broadening of a propagating parton in an inhomogeneous medium. Such broadening is studied within a path integral description of the evolution of the Wigner distribution for a propagating parton in medium. Going beyond the eikonal approximation of multiple scattering, the evolution operator in the transverse direction can be expressed as the functional integration over all classical trajectories of a massive particle with the light-cone momentum $ω$ as its mass. With a dipole approximation of the Wilson line correlation function, evolution with the light-cone time $t$ is determined by the jet transport coefficient $\hat q$ that can vary with space and time. In a uniform medium with a constant $\hat q_0$, the analytical solution to the Wigner distribution becomes a typical drifted Gaussian in both transverse momentum and coordinate with the diffusion width $\sqrt{\hat q_0t}$ and $\sqrt{\hat q_0t^3/3ω^2}$, respectively. In the case of a simple Gaussian-like transverse inhomogeneity with a spatial width $σ$ on top of a uniform medium, the final asymmetrical momentum distribution can be calculated semi-analytically. The transverse asymmetry defined for jet gradient tomography that characterizes the asymmetrical distribution is found to linearly correlate with the initial transverse position of the propagating parton within the domain of the inhomogeneity. It decreases with the parton energy $ω$, increases with the propagation time initially and saturates when the diffusion distance is much larger than the size of the inhomogeneity or $t^3\gg 3ω^2σ^2/\hat q_0$. The transverse momentum broadening due to the inhomogeneity also saturates at late time in contrast to the continued increase with time if the drifted diffusion in space is ignored.

hep-ph↗

arXiv2022

A resource-efficient deep learning framework for low-dose brain PET image reconstruction and analysis

18F-fluorodeoxyglucose (18F-FDG) Positron Emission Tomography (PET) imaging usually needs a full-dose radioactive tracer to obtain satisfactory diagnostic results, which raises concerns about the potential health risks of radiation exposure, especially for pediatric patients. Reconstructing the low-dose PET (L-PET) images to the high-quality full-dose PET (F-PET) ones is an effective way that both reduces the radiation exposure and remains diagnostic accuracy. In this paper, we propose a resource-efficient deep learning framework for L-PET reconstruction and analysis, referred to as transGAN-SDAM, to generate F-PET from corresponding L-PET, and quantify the standard uptake value ratios (SUVRs) of these generated F-PET at whole brain. The transGAN-SDAM consists of two modules: a transformer-encoded Generative Adversarial Network (transGAN) and a Spatial Deformable Aggregation Module (SDAM). The transGAN generates higher quality F-PET images, and then the SDAM integrates the spatial information of a sequence of generated F-PET slices to synthesize whole-brain F-PET images. Experimental results demonstrate the superiority and rationality of our approach.

eess.IV↗

arXiv2022

Activate index: an integrated index to reveal disrupted brain network organizations of major depressive disorder patients

Altered functional brain networks have been a typical manifestation that distinguishes major depressive disorder (MDD) patients from healthy control (HC) subjects in functional magnetic resonance imaging (fMRI) studies. Recently, rich club and diverse club metrics have been proposed for network or network neuroscience analyses. The rich club defines a set of nodes that tend to be the hubs of specific communities, and the diverse club defines the nodes that span more communities and have edges diversely distributed across different communities. Considering the heterogeneity of rich clubs and diverse clubs, combining them and on the basis to derive a novel indicator may reveal new evidence of brain functional integration and separation, which might provide new insights into MDD. This study for the first time discussed the differences between MDD and HC using both rich club and diverse club metrics and found the complementarity of them in analyzing brain networks. Besides, a novel index, termed "active index", has been proposed in this study. The active index defines a group of nodes that tend to be diversely distributed across communities while avoiding being a hub of a community. Experimental results demonstrate the superiority of active index in analyzing MDD brain mechanisms.

q-bio.NC↗

arXiv2021

Biconservative hypersurfaces with constant scalar curvature in space forms

Biconservative hypersurfaces are hypersurfaces which have conservative stress-energy tensor with respect to the bienergy, containing all minimal and constant mean curvature hypersurfaces. The purpose of this paper is to study biconservative hypersurfaces $M^n$ with constant scalar curvature in a space form $N^{n+1}(c)$. We prove that every biconservative hypersurface with constant scalar curvature in $N^4(c)$ has constant mean curvature. Moreover, we prove that any biconservative hypersurface with constant scalar curvature in $N^5(c)$ is ether an open part of a certain rotational hypersurface or a constant mean curvature hypersurface. These solve an open problem proposed recently by D. Fetcu and C. Oniciuc for $n\leq4$.

math.DG↗

arXiv2021

Thermalization of non-abelian gauge theories at next-to-leading order

We provide the first next-to-leading-order (NLO) weak-coupling description of the thermalization process of far-from-equilibrium systems in non-abelian gauge theory. We study isotropic systems starting from either over- or under-occupied initial conditions and follow their time evolution towards thermal equilibrium by numerically solving the QCD effective kinetic theory at NLO accuracy. We find that the NLO corrections remain well under control for a wide range of couplings and that the overall effect of NLO corrections is to reduce the time needed to reach thermal equilibrium in the systems considered.

hep-ph↗

arXiv2021

Dual-Phase MoS$_2$ And MXene Nanohybrids for Efficient Electrocatalytic Hydrogen Evolution

Molybdenum Disulfide (MoS$_2$) has been recognized as a potential substitution of Platinum (Pt) for electrochemical hydrogen evolution reaction (HER). However, the broad adoption of MoS$_2$ is hindered by its limited number of active sites and relatively low inherent electrical conductivity. In this work, we demonstrated a synergistic enhancement of both active site exposure and electrical conductivity by a one-step solvothermal synthesis technique. The 1T-phase enriched MoS$_2$ was directly formed on the titanium carbide (Ti$_3$C$_2$Tx, MXene) with carbon nanotubes (CNTs) acting as crosslinks. The existence of edge-enriched metallic phase MoS$_2$, the conductive backbone of MXene along with the crosslinking function of CNTs clearly improved the overall electrical conductivity of the catalyst. Moreover, the integration of two-dimensional (2D) MoS$_2$ with MXene effectively suppressed the MXene oxidation and 2D layer restacking, leading to good catalytic stability. As a result, an overpotential of 169 mV and a low Tafel slope of 51 mV/dec was successfully achieved. This work provides a new route for 2D-based electrocatalyst engineering and sheds light on the development of the next-generation PGM-free HER electrocatalysts.

physics.chem-ph↗

arXiv2021

Understanding the Effects of Visualizing Missing Values on Visual Data Exploration

When performing data analysis, people often confront data sets containing missing values. We conducted an empirical study to understand the effects of visualizing those missing values on participants' decision-making processes while performing a visual data exploration task. More specifically, our study participants purchased a hypothetical portfolio of stocks based on a dataset where some stocks had missing values for attributes such as PE ratio, beta, and EPS. The experiment used scatterplots to communicate the stock data. For one group of participants, stocks with missing values simply were not shown, while the second group saw such stocks depicted with estimated values as points with error bars. We measured participants' cognitive load involved in decision-making with data with missing values. Our results indicate that their decision-making workflow was different across two conditions.

cs.HC↗

arXiv2021

RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection

The novel 2019 Coronavirus (COVID-19) infection has spread world widely and is currently a major healthcare challenge around the world. Chest Computed Tomography (CT) and X-ray images have been well recognized to be two effective techniques for clinical COVID-19 disease diagnoses. Due to faster imaging time and considerably lower cost than CT, detecting COVID-19 in chest X-ray (CXR) images is preferred for efficient diagnosis, assessment and treatment. However, considering the similarity between COVID-19 and pneumonia, CXR samples with deep features distributed near category boundaries are easily misclassified by the hyper-planes learned from limited training data. Moreover, most existing approaches for COVID-19 detection focus on the accuracy of prediction and overlook the uncertainty estimation, which is particularly important when dealing with noisy datasets. To alleviate these concerns, we propose a novel deep network named {\em RCoNet$^k_s$} for robust COVID-19 detection which employs {\em Deformable Mutual Information Maximization} (DeIM), {\em Mixed High-order Moment Feature} (MHMF) and {\em Multi-expert Uncertainty-aware Learning} (MUL). With DeIM, the mutual information (MI) between input data and the corresponding latent representations can be well estimated and maximized to capture compact and disentangled representational characteristics. Meanwhile, MHMF can fully explore the benefits of using high-order statistics and extract discriminative features of complex distributions in medical imaging. Finally, MUL creates multiple parallel dropout networks for each CXR image to evaluate uncertainty and thus prevent performance degradation caused by the noise in the data.

eess.IV↗

arXiv2021

A Dual-branch Network for Infrared and Visible Image Fusion

Deep learning is a rapidly developing approach in the field of infrared and visible image fusion. In this context, the use of dense blocks in deep networks significantly improves the utilization of shallow information, and the combination of the Generative Adversarial Network (GAN) also improves the fusion performance of two source images. We propose a new method based on dense blocks and GANs , and we directly insert the input image-visible light image in each layer of the entire network. We use SSIM and gradient loss functions that are more consistent with perception instead of mean square error loss. After the adversarial training between the generator and the discriminator, we show that a trained end-to-end fusion network -- the generator network -- is finally obtained. Our experiments show that the fused images obtained by our approach achieve good score based on multiple evaluation indicators. Further, our fused images have better visual effects in multiple sets of contrasts, which are more satisfying to human visual perception.

cs.CV↗