Deep neural networks, such as the deep-FSMN, have been widely studied for keyword
spotting (KWS) applications while suffering expensive computation and storage. Therefore …

Visible-infrared person re-identification (VI-ReID) aims at matching people across images
from RGB and infrared modality. Existing methods tend to utilize the readily available …

Transformer is extensively employed in natural language processing, and computer vision
(CV), with the self-attention structure. Due to its outstanding long-range dependency …

Introduction Fast-emerging technologies are making the job market dynamic, causing
desirable skills to evolve continuously. It is therefore important to understand the transitions …

The Retinex model is one of the most representative and effective methods for low-light
image enhancement. However, the Retinex model does not explicitly tackle the noise …

During the operation of high-speed trains, some vehicles will experience wheel
polygonization (WP). Severe polygonal wear significantly increases the wheel-rail contact …

Mixture of symmetric-stable (ss) models can be used to model impulsive data with heavy-
tailed distribution. Lack of closed-form expression for-stable distributions is a challenge for …

The finite inverted beta mixture model (IBMM) has been proven to be efficient in modeling
positive vectors. Under the traditional variational inference framework, the critical challenge …

针对I-niceMO 算法在候选聚类中心合并时中心数目难以确定和中心点识别不准确的问题,
提出了基于夹角几何的I-niceMO 增强(I-niceMOEn) 算法. 利用观测点与数据点之间的距离和 …

To exactly determine the number of cluster centers and correctly identify the candidate
cluster centers, an I-niceMO enhanced (I-niceMOEn) algorithm based on intersection angel …