This paper studies the problem of event-triggered impulsive tracking control (ETITC) for uncertain strict-feedback nonlinear systems (USFNSs). In contrast to existing impulsive control schemes, this paper incorporates the neural-network (NN)-...

Automatic detection of kitchen waste enables the identification and quantification of non-degradable materials, such as plastics, metals, and other substances that cannot be easily decomposed. This approach increases the efficiency of the waste ...

Accurate and reliable automatic segmentation of lesion areas in gastroscopy images can assist endoscopists in making diagnoses and reduce the possibility of missed or incorrect diagnoses. This paper presents a two-stage framework for segmenting ...

Image super-resolution (SR) is a crucial task in computer vision that involves reconstructing a low-resolution (LR) image into its high-resolution (HR) counterpart. Transformer-based methods excel at establishing long-range dependency but face ...

In recent years, there has been a growing interest in the widespread application of graph neural networks (GNNs). However, existing GNN frameworks are predominantly designed for simple graphs in Euclidean space, limiting their effectiveness in ...

• We introduced the hypergraph model into the graph convolutional neural network.
• We extended the representation learning of the HHGNN model to non-Euclidean space.
• We conducted large-scale experiments to comprehensively evaluate the ...

The language-based moment localization (LBML) goal is to locate the moment that corresponds to the input query, and output is the moment that matches with the input query. Due to erroneous correlations between various modalities, currently ...

The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying objects ...

In this paper, the fixed-time stability of general impulsive systems and the fixed-time synchronization issue of impulsive complex networks are investigated. First, the fixed-time stability of a class of nonlinear systems with general impulsive ...

Deep Neural Networks achieve outstanding results; however, their reliance on a static environment with fixed data poses challenges in dynamic scenarios where data continuously evolves. Being capable of learning, adapting, and generalizing ...

The field of deep learning is renowned for its resource-intensive nature, hence improving its environmental impact is crucial. In this paper, we propose a novel model compression method to mitigate the energy demands of deep learning for a ...

• Novel method for extreme quantization in deep learning medical classification models.
• Differentiable asymmetric pruning based on the statistics of the weights.
• Better trade-of between the compression, energy, and classification ...

With the end of the COVID-19 pandemic, the number of pedestrians in various public places has increased dramatically. Estimating the size and density distribution of crowds accurately from images is essential for public safety. At present, there ...

With modern industrial processes becoming more and more complex, the occurrence of faults may cause unmitigated disaster. Therefore, incipient fault detection is very important and has attracted increasing attention Recently, a feature ensemble ...

• A dense ensemble network that reuses shallow information is proposed.
• Several unsupervised base detectors with machine learning are constructed.
• The computational complexity of this method is analyzed.
• The effectiveness of the ...

We consider the problem of spectral clustering under group fairness constraints, where samples from each sensitive group are approximately proportionally represented in each cluster. Traditional fair spectral clustering (FSC) methods consist of ...

• The effect of similarity graphs on fair spectral clustering is theoretically analyzed.
• A graph construction method to learn graphs from potentially noisy data is proposed.
• A dual Laplacian framework for unified fair spectral ...

Depression, a common mental disorder, significantly influences individuals and imposes considerable societal impacts. The complexity and heterogeneity of the disorder necessitate prompt and effective detection, which nonetheless, poses a ...

Compared to the untargeted attack, the targeted attack is a more challenging task in the field of adversarial attacks for object detection, because it aims to mislead the detectors to predict certain specific wrong labels rather than arbitrary ...

• Low fooling rates when target classes differ from victim classes limit attack performance.
• A new framework attacks the object’s feature and contextual information simultaneously.
• Achieving large improvement of fooling rates in ...

High-quality 3D reconstruction is becoming increasingly important in a variety of fields. Recently, implicit representation methods have made significant progress in image-based 3D reconstruction. However, these methods tend to yield entangled ...

With the rapid development of deep convolutional networks, attributed graph clustering has become an increasingly important and challenging research area. In the field of graph clustering, more and more researchers have recognized the role of ...

• We propose a novel method for integrating content and structure via layer fusion.
• We use adversarial regularization in graph clustering to improve robustness.
• We design a joint self-supervised module and analyze its sensitivity to ...

Artificial intelligence, and especially deep neural networks, have evolved substantially in the recent years, infiltrating numerous domains of applications, often greatly impactful to society’s well-being. As a result, the need to understand how ...

Multi-objective optimization problem (MOP) plays an increasingly important role in finance and engineering. In order to obtain more accurate and evenly distributed target solution set to a multi-objective programming, a novel swarm exploring ...

Unsupervised feature selection (UFS) aims to identify a subset of the most informative features from high-dimensional data without labels. However, most existing UFS methods cannot adequately capture the intricate nonlinear relationships present ...