Deep learning algorithms have exhibited impressive performance across various computer
vision tasks; however, the challenge of overfitting persists, especially when dealing with …

High-resolution remotely sensed images pose challenges to traditional semantic
segmentation networks, such as Convolutional Neural Networks (CNNs) and Vision …

Deep learning methods, especially convolutional neural networks (CNNs) and vision
transformers (ViTs), are frequently employed to perform semantic segmentation of high …

Data augmentation is a crucial technique for expanding training datasets, effectively
alleviating the overfitting issue that arises from limited training data in deep learning models …

The goal of this document is to survey existing methods for recovering or extracting CSG
(Constructive Solid Geometry) representations from unstructured data such as 3D point …

Recent advancements in autoregressive networks with linear complexity have driven
significant research progress, demonstrating exceptional performance in large language …

Ensuring the freshness of fruits and vegetables in a sustainable agricultural supply chain
network (SASCN) presents complex challenges that require integrated solutions with …

Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-
temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs …

Environmental monitoring of lakeside green areas is crucial for environmental protection.
Compared to manual inspections, computer vision technologies offer a more efficient …

Point cloud semantic segmentation, the process of classifying each point into predefined
categories, is essential for 3D scene understanding. While image-based segmentation is …