As a critical preprocessing step, hyperspectral image (HSI) denoising aims to improve the HSI quality for subsequent applications. While unsupervised HSI denoising methods based on Deep Image Prior (DIP) have garnered attention due to their pre-training-free advantage, existing DIP-based approaches typically utilizeL2-norm as data fidelity, making them inefficient in handling complex mixed noise. Moreover, such unsupervised methods only focus on spatial domain priors, lacking a comprehensive characterization of the spatial-spectral correlations inherent in HSIs. To tackle these limitations, we propose a robust deep recovery (RDR) model for HSI denoising with spatial-spectral total generalized variation (SSTGV) prior. Specifically, the truncated-Cauchy loss function is adopted to suppress the interference of outliers and enhance the robustness against sparse noise. Moreover, the SSTGV prior is integrated into the unsupervised RDR model, resulting in complementary effect of deep prior and handcraft prior. To solve the resulting optimization problem, an efficient ADMM algorithm is developed with convergence guarantee. Experimental results demonstrate the significant advantages of our approach in both noise suppression and detail preservation, highlighting its robustness and adaptability for varied HSI denoising applications.

Gesture recognition provides an effective human-computer interaction that makes device control more intuitive and convenient. Although the research on mmWave radar-based gesture recognition has demonstrated promising results, existing studies have exclusively addressed the cross-domain challenge or the human activity interference problem, and no attention has been paid to the cross-domain problem in the presence of human activity interference. To address these issues, we propose a novel mmWave radar-based gesture recognition system, named GestSAM, which leverages a parameter-free attention mechanism to effectively extract gesture features that are less affected by environmental noise. By integrating this mechanism with deep learning techniques, GestSAM significantly reduces the impact of human activity interference while maintaining robust cross-domain gesture recognition performance. This approach ensures robust, high-accuracy recognition of gestures. In order to evaluate the performance of our system, we construct a dataset containing six different gesture types performed by fifteen volunteers in seven different scenarios and simulate three interference conditions. The experimental results show that under human activity interference, the model achieves average recognition accuracies of 92.79% and 94.62% in cross-user and cross-scenario, respectively.

With the maturation of Deep Learning-based Video Frame Interpolation (Deep VFI), the left spatial-temporal inconsistency in the synthesis process is greatly improved, which poses a challenge to the current VFI detector. This article presents a dual-stream identification network based on Bi-level Routing Attention and enhanced Spatial-Temporal inconsistency learning (BRA-ST) to address this challenge. Specifically, the spatial inconsistencies in Deep VFI are mainly reflected in their motion regions and moving object edges; thus, the high-pass filter is introduced to enhance them, facilitating the three-stage pyramid structure of BiFormer Blocks with bi-level routing attention in the frame-level stream to learn. To fully exploit the temporal inconsistencies in the Deep VFI video, the time-difference module in the time-level stream is superimposed with the ConvGRU to extract the temporally dependent features of continuous multiple frames. Additionally, the middle layer of the two streams interacts and aggregates with the channel attention, and then, their last layer adaptively merges from a whole and part perspective for the ultimate frame prediction. Finally, the experimental findings on a constructed dataset by the five most advanced Deep VFI methods indicate that the proposed BRA-ST achieved \(F_{\text{1Score}}\) of 99.73%, which is superior to the existing Deep VFI detectors, and further verify that the resolution of BRA-ST for different Deep VFI methods reached 78.55%. Our source codes and dataset are available at https://pan.baidu.com/s/1f05_gS0qu5G-SSIkd9F4Hw?pwd=j6t6 .

High Efficiency Video Coding (HEVC) is a recent yet increasing widely-used video coding standard, and double compression detection is usually an essential step to verify the integrity of HEVC-encoded videos. However, it is challenging due to fewer traces left by HEVC double compression with the same parameters. Moreover, existing full-supervised learning works for HEVC double compression detection are inefficient because they depend on large amounts of labeled pristine and forged videos, which are difficult to be collected. To address these issues, a One-Class Classification (OCC)-based hybrid heterogeneous network is proposed, which only needs the pristine videos. We first develop a modulation layer with both motion alignment and high-frequency preservation operations, which serves as an effective metric to evaluate the differences between those videos compressed once and twice. Then, a heterogeneous network with a shallow Convolutional Neural Network (CNN) and a six-node Graph Neural Network (GNN) is proposed. Specifically, the shallow CNN, which pays more attention to medium or fast-motion regions, learns from subtle fluctuations of pixel values caused by double compression, whereas GNN, which focuses on static and slow-motion regions, is developed to represent the local-global relationship of video patches and the distribution of zero-value pixels in the high-frequency components of motion-aligned residuals. Due to the motion-aware mechanism, the proposed approach only learns features from single compressed videos. Extensive experimental results show that the proposed approach outperforms the state-of-the-art full-supervised learning works and other more complex OCC works.

Impulsive noise is always present in real-world image Compressive Sensing (CS) acquisition systems, where existing CS reconstruction performance may seriously deteriorate. In this article, we propose a robust CS formulation for image reconstruction to suppress outliers in the presence of impulsive noise. To address this issue, we consider a novel truncated-Cauchy loss function as the metric of residual error to elevate the reconstruction robustness. Specifically, we design a complementary priors model to incorporate nonconvex nonlocal low-rank prior and deep denoiser prior for high-accuracy image reconstruction. By means of the half-quadratic optimization theory and generalized soft-thresholding technique, we also develop an alternative optimization algorithm for solving the induced nonconvex optimization problem. Numerical simulations demonstrate the robustness and accuracy of the proposed robust CS method compared to some recent CS methods for image reconstruction in impulsive noise.

Early detection of lung nodules is an important means of reducing the lung cancer mortality rate. In this paper, we propose a three‐dimensional CT image lung nodule detection method based on parallel pooling and dense blocks, which includes two parts, i.e., candidate nodule extraction and false positive suppression. First, a dense U‐shaped backbone network with parallel pooling is proposed to obtain the candidate nodule probability map. The parallel pooling structure uses multiple pooling operations for downsampling to capture spatial information comprehensively and address the problem of information loss resulting from maximum and average pooling in the shallow layers. Then, a parasitic network with parallel pooling, dense blocks, and attention modules is designed to suppress false positive nodules. The parasitic network takes the multiscale feature maps of the backbone network as the input. The experimental results demonstrate that the proposed method significantly improves the accuracy of lung nodule detection, achieving a CPM score of 0.91, which outperforms many existing methods.

Sequential recommendation has been a widely popular topic of recommender systems. Existing works have contributed to enhancing the prediction ability of sequential recommendation systems based on various methods, such as recurrent networks and self-attention mechanisms. However, they fail to discover and distinguish various relationships between items, which could be underlying factors which motivate user behaviors. In this article, we propose an Edge-Enhanced Global Disentangled Graph Neural Network (EGD-GNN) model to capture the relation information between items for global item representation and local user intention learning. At the global level, we build a global-link graph over all sequences to model item relationships. Then a channel-aware disentangled learning layer is designed to decompose edge information into different channels, which can be aggregated to represent the target item from its neighbors. At the local level, we apply a variational auto-encoder framework to learn user intention over the current sequence. We evaluate our proposed method on three real-world datasets. Experimental results show that our model can get a crucial improvement over state-of-the-art baselines and is able to distinguish item features.

An increased awareness concerning risks of algorithmic bias has driven a surge of efforts around bias mitigation strategies. A vast majority of the proposed approaches fall under one of two categories: (1) imposing algorithmic fairness constraints on predictive models, and (2) collecting additional training samples. Most recently and at the intersection of these two categories, methods that propose active learning under fairness constraints have been developed. However, proposed bias mitigation strategies typically overlook the bias presented in the observed labels. In this work, we study fairness considerations of active data collection strategies in the presence of label bias. We first present an overview of different types of label bias in the context of supervised learning systems. We then empirically show that, when overlooking label bias, collecting more data can aggravate bias, and imposing fairness constraints that rely on the observed labels in the data collection process may not address the problem. Our results illustrate the unintended consequences of deploying a model that attempts to mitigate a single type of bias while neglecting others, emphasizing the importance of explicitly differentiating between the types of bias that fairness-aware algorithms aim to address, and highlighting the risks of neglecting label bias during data collection.

Matrix completion-assisted channel estimation is considered one of promising techniques in millimeter wave (mmWave) massive multiple input multiple output (MIMO) system by exploiting the low-rank property of channel matrix in the angle domain. However, existing channel estimation approaches are hard to achieve high accuracy due to the inevitable bias solution caused by nuclear norm based minimization (NNM). To address this problem, this paper proposes a novel matrix completion-assisted mmWave massive MIMO channel estimation method. We employ an effective and flexible rank function named joint weighted and truncated nuclear norm as relaxation of nuclear norm, and then construct an novel matrix completion model for channel estimation problem. Moreover, a popular framework of alternating direction method of multipliers (ADMM) is derived for minimization of the resulting optimization problem. Simulation results are provided to verify the proposed method that can flexibly and effectively improve the channel estimation accuracy with reliable convergence.

This article proposes a new method that enables Unmanned Aerial Vehicles (UAVs) to actively find targets and shoot photographs of them in an unknown environment, while successfully avoiding surrounding obstacles and planning optimize routes. Owing to the limited computing ability on the UAVs, we obtained the point cloud data of surrounding objects, and selected the best segmentation method of the point cloud to perform real-time semantic segmentation on the collected point cloud data. The point cloud data with semantic attributes were merged into voxels. We reconstruct the real-time distance and angle between the surface of obstacles and the surrounding obstacles through Euclidean Signed Distance Fields (ESDFs), and adjust the gimbal angle and focal length of UAVs and use the two-dimensional image recognition to shoot the photographs of the target precisely. Considering the increasing scale of UAVs power inspections, we can improve the efficiency of fine inspections of power transmission lines by using the method we proposed.

Video segmentation aims to segment target objects in a video sequence, which remains a challenge due to the motion and deformation of objects. In this paper, we propose a novel attention-driven hybrid encoder-decoder network that generates object segmentation by fully leveraging spatial and temporal information. Firstly, a multi-branch network is designed to learn feature representation from object appearance, location and motion. Secondly, a target attention module is proposed to further exploit context information from learned representation. In addition, a novel edge loss is designed which constraints the model to generate salient edge features and accurate segmentation. The proposed model has been evaluated over two widely used public benchmarks, and experiments demonstrate its superior robustness and effectiveness as compared with the state of the arts.

The purpose of video segmentation is to segment foreground objects from a video sequence. In this paper, we propose a CNN based method for the semi-supervised video object segmentation, where a hybrid encoder-decoder network is designed to generate pixel-wise foreground object segmentation in use of both spatial and temporal information. In order to minimize cumulative error of the network as much as possible, we develop a two-stage training scheme: alternate training and back-propagation-through-time training. Then the performances of our method and other state-of-the-art ones are compared on two annotated video segmentation databases. Furthermore, we also run an extensive ablation study to test the effects of different components from our method.

The objectiveness of Traditional Chinese Medicine (TCM) limits its further development and generalization. Big data provide the golden opportunity for TCM quantization. The main purpose of this paper is to build a bridge between data analysis and clinical experience and provide experimental support for TCM experience. Taking the Hepatitis B disease data as experimental subject, we propose a framework for mining latent relations between features and disease categories based on Granular Computing theory. That is, kmeans clustering and correlation analysis is adopted to analyze the intra-relationship of disease stages and relationship between clinical symptoms and stages respectively. Algorithm based on Latent Dirichlet Allocation model is proposed to mining the mapping relationships of the three layers: clinical symptoms, stages of Hepatitis B and their middle layer syndromes. Experimental results indicate that the results of the data analysis are consistent with the clinical experience of TCM. It is proved that the diagnose based on syndromes is the scientific results of manually mining large amount of history data. Our study is a useful attempt that using data mining techniques to make TCM quantifiable and objective.

A mission of chemical plume tracing (CPT) in near-shore and ocean environments is to find out an odor source via an autonomous underwater vehicle (AUV). It is necessary to confirm the detected odor source using a visual system interactively or automatically, when a chemical sensor identifies the odor source. However, color images taken in near-shore ocean environments are very vague due to dim illumination conditions and fluid advection effects. This paper presents a fuzzy algorithm for recognizing the chemical plume and its source in near-shore and ocean environments. This algorithm iteratively generates color patterns based on a defined reference color and extracts color components of the chemical plume and its source from fuzzy images using a fuzzy color extractor (FCE). The proposed approach to color image segmentation might be of general interest to robot vision.