Search Results

Label Distribution Learning (LDL) leverages label distribution (LD) to represent instances, which helps solve label ambiguity. However, obtaining LD can be extremely challenging in many real-world scenarios. Label Enhancement (LE) has emerged as ...

• Introduced Progressive Label Enhancement for integrating label distribution and reduction.
• Optimized feature space by filtering noise and leveraging manifold structures.
• Combined dependency-maximization reduction with label ...

Quickly obtaining and classifying relevant information about crisis events via social media platforms, such as Twitter and Weibo, plays a critical role in the subsequent rescue operations and post-disaster reconstruction. Current crisis event ...

The H ∞ state estimation problem for discrete-time Takagi–Sugeno (T–S) fuzzy-affine systems with Denial-of-Service (DoS) attacks whose occurrence is described by persistent dwell-time (PDT) switched model is discussed in this work. It should be ...

The significance of Driver Distraction Detection (DDD) in enhancing road safety is immense and undeniable. While numerous DDD methods concentrate on conventional distractions, such as driving behavior, gaze direction, or hand movements, they ...

• Temporal-aware preprocessing enhances representation of driver eye data sequences.
• FAN: Fusion Adversarial Network for Efficient DCI and Map Feature Integration.
• MSCN: Multi-View Space Channel Network integrates space channel ...

A fractional partial differential denoising model for ultrasound image and its corresponding finite difference optimization solution algorithm are proposed. The model combines the advantages of the total variational and the fourth-order partial ...

Long-term Time Series Forecasting (LTSF) plays a crucial role in real-world applications for early warning and decision-making. Time series inherently embody complex semantic information, including segment semantics, global–local semantics, and ...

• A long-term time-series forecasting method considering multi-semantic information is proposed.
• Being more efficient than existing multi-semantic long-term forecasting models.
• Achieving sota performance across multiple mainstream ...

Label Distribution Learning (LDL) is a novel learning paradigm that assigns label distribution to each instance. It aims to learn the label distribution of training instances and predict unknown ones. Algorithm Adaptation (AA)-kNN is one of the ...

• Residual label distribution learning. We propose residual label distribution and design residual label distribution learning.
• Neighborhood structure of label distribution. We propose to exploit the neighborhood structure of label ...

Multivariate time series classification (MTSC), which identifies categories of multiple sensor signals recorded in continuous time, is widely used in various fields such as transportation, finance, and medical treatment. The focused challenge ...

Discovering the intrinsic structure of incomplete data is a significant challenge in machine learning. When data incompleteness results in high sparsity levels and samples exhibiting varying degrees of missing data, traditional data processing ...

Knowledge tracing (KT) is a crucial educational tool that models students’ mastery of various knowledge concepts by analyzing their historical learning records. Mainstream studies have turned to Deep Neural Networks (DNNs) to effectively trace ...

Efficiently searching for novel molecules with specific properties is critical to molecular generation. Some existing works focus on combining deep generative models and reinforcement learning to generate molecules with targeted properties, but ...

• Propose improved reward-shaping to address reward sparsity in molecular generation.
• Enable the agent to efficiently explore in a vast chemical space.
• Use intrinsic rewards obtained by exploration for self-supervised learning.
• ...

The generalized k-connectivity of a graph G, denoted by κ k ( G ), is the minimum number of internally disjoint S-trees for any S ⊆ V ( G ) and | S | = k. The generalized k-connectivity is a natural extension of the classical connectivity and ...

Random walk is a powerful tool for large-scale graph learning, but its high computational demand presents a challenge. While GPUs can accelerate random walk tasks, current frameworks fail to fully utilize GPU parallelism due to memory-to-compute bandwidth ...

As the automotive industry evolves towards greater technological intelligence, multimodal in-vehicle interaction systems introduce new challenges, particularly in managing system latency-the delay between user input and system response. This study aims ...

Zero-shot learning (ZSL) aims to identify new classes by transferring semantic knowledge from seen classes to unseen classes. However, existing models lack a differentiated understanding of different attributes and ignore the impact of global ...

• Construct a Multi-granularity Contrastive Zero-shot Learning Model Based on Attribute Decomposition.
• Introduce the global–local paradigm into the zero-shot image classification task, proposing a multi-granularity contrastive learning ...

Concerns surrounding privacy leakages caused by prevalent vision-based person identifications are countless. A promising privacy-preserving solution is to identify the wireless signals reflecting persons, which, however, faces a major challenge of losing ...

Periodically monitoring the pavement cracks is of great importance to many transportation infrastructures. This paper proposed an unsupervised deep-learning-based method to match the cracks in multi-temporal unmanned aerial vehicle (UAV) images and ...

Graph Neural Networks (GNNs) are playing an increasingly vital role in the field of recommender systems. To improve knowledge perception within GNNs, contrastive learning has been applied and has proven to be highly effective. GNNs have the ...

Multi-objective evolutionary algorithms (MOEAs) are widely employed to tackle multi-objective optimization problems (MOPs). However, the choice of different crossover operators significantly impacts the algorithm's ability to balance population ...

• A fuzzy fusion module is designed based on Choquet integral in fuzzy theory.
• A collaborative convolutional fusion layer is proposed to enhance the complementary information.
• The characteristics of different loss functions are ...

Brain age gap can be estimated from brain images, serving as a valuable biomarker for aging-associated diseases, using deep neural networks. Traditional brain age prediction methods tend to rely on unimodal data. Multimodal data can provide more ...