Few-shot image classification is a challenging topic in pattern recognition and computer vision. Few-shot fine-grained image classification is even more challenging, due to not only the few shots of labelled samples but also the subtle ...

• We propose AFRN, a simple scheme to amplify inter-class discrepancy.
• We relax the inter-class score in TDM to mitigate the negative impact of overfitting.
• We incorporate the guidance of the centre loss to FRN to enhance the ...

After detecting different external light stimuli, photosensitive neurons encode these stimuli and trigger different discharge patterns and membrane potentials, thereby transmitting signals in the neural network. The cross-ring structure can ...

Color-guided depth map super-resolution (CDSR) improves the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and augmented ...

• We propose the first diffusion model-based framework for depth map super-resolution.
• The diffusion model in our DSR-Diff is significantly efficient in computation and is highly flexible in usage.
• DSR-Diff alleviates the impact of ...

A key aspect of asset investment and risk management is the study of forecasting stock prices. We investigate the machine learning stock price prediction in a new hybrid neural network model and put forth a forecasting method based on machine ...

• A new hybrid forecasting model is proposed based on machine learning.
• Convolutional layers are added to neural network for extracting local information.
• The CEEMDAN algorithm and SG filters are applied to preprocess input data.

• A transform-based feature reconstruction network is designed for missing modalities.
• The model reconstructs missing element features to improve the robustness.
• Modality-invariant representation is used in missing modalities.
• ...

The investigation of missing modalities aims to extract valuable feature information from missing multi-modal data, it is a focal point in multi-modal learning. Existing missing modalities processing methods primarily focused on multi-modal ...

In this paper, we study the problem of update repair under integrity constraints. For a set of inconsistent data, update repair modifies the attribute values of inconsistent tuples such that the modified data no longer violate the constraints. ...

How to avoid congested roads and spend the least time to reach the destination has become an urgent requirement for citizens. When large-scale origin-destination queries arrive, these queries themselves will affect road congestion. Therefore, it ...

Large pre-trained models, also known as foundation models (FMs), are trained in a task-agnostic manner on large-scale data and can be adapted to a wide range of downstream tasks by fine-tuning, few-shot, or even zero-shot learning. Despite their successes ...

Developing chatbots as personal companions has long been a goal of artificial intelligence researchers. Recent advances in Large Language Models (LLMs) have delivered a practical solution for endowing chatbots with anthropomorphic language capabilities. ...

Lithology identification is a crucial task for reservoir characterization and evaluation. There exists an intricate non-linear response between formation lithology and logging data. However, it is difficult to avoid lithology mislabeling due to ...

In the era of globalization and technological progress, distance online learning has become a vital educational trend, accentuated by the COVID-19 pandemic. Taiwan has strategically embraced the development of distance learning, especially for high ...

In this paper, the minimum-time strategy optimization problem for NEGs with bankruptcy mechanism is considered based on semi-tensor product of matrices. Firstly, in order to describe the impact of bankruptcy mechanism on evolution, a novel matrix ...

• The minimum-time control is first introduced into the study of NEGs.
• The introduction of heterogeneous memory expands NEGs with bankruptcy mechanism.
• A new approach is proposed to study NEGs with bankruptcy mechanism.
• The new ...

Driver Distraction Detection (3D) is of great significance in helping intelligent vehicles decide whether to remind drivers or take over the driving task and avoid traffic accidents. However, the current centralized learning paradigm of 3D has become ...

Blockchain is a trans-generational technology that is gradually introduced and applied in many fields because of its characteristics such as tamper-proof, traceability, and decentralization. However, the performance bottlenecks of blockchain have been one ...

Simulation built upon partial and ordinary differential equations has been a classic approach to modeling cardiac electrophysiological dynamics. However, mitigating the computational burden of differential equations is still a challenging problem. This ...

As we know that simply applying existing techniques in process mining will often yield a highly incomprehensible process model that called the spaghetti-like model, because real-life processes are typically less structured and more complex than ...

k-closest pair (KCP for short) search is a fundamental problem in database research. Given a set of d-dimensional streaming data S, KCP search aims to retrieve k pairs with the shortest distances between them. While existing works have studied continuous ...

The topic of knowledge graphs (KGs) has recently attracted extensive attention in both industry and academia. Knowledge graphs are a new paradigm for representing, retrieving, integrating, and reasoning data from highly heterogeneous and multimodal ...

Knowledge graphs (KG) are used for many downstream tasks in artificial intelligence (AI). However, owing to accuracy issues associated with information extraction, KGs are often incomplete. This has led to the emergence of knowledge graph ...

Recently, the keyword-aware routing problem has been increasingly studied, which is to return the optimal route from the starting point s to the destination t, satisfying all the user-specified keyword requirements. Most existing solutions focus ...