Contemporary multi-modal trackers achieve strong performance by leveraging complex backbones and fusion strategies, but this comes at the cost of computational efficiency, limiting their deployment in ...

The transport sector has experienced a boom in electric mobility over the past decade as it moves towards a more sustainable future associated with the Sustainable Development Goals (SDGs). This paper ...

Since higher-order tensors are naturally suitable for representing multi-dimensional data in real-world, e.g., color images and videos, low-rank tensor representation has become one of the emerging ...

Single image dehazing is a challenging ill-posed problem which estimates latent haze-free images from observed hazy images. Some existing deep learning based methods are devoted to improving the model ...

Motorimagery EEG classification plays a crucial role in non-invasive Brain-Computer Interface (BCI) research. However, the performance of classification is affected by the non-stationarity and ...

This letter presents Switch-SLAM, switching-based LiDAR-inertial-visual SLAM for degenerate environments, designed to tackle the challenges in degenerate environments for LiDAR and visual SLAM. Switch ...

Underwater imaging is often affected by light attenuation and scattering in water, leading to degraded visual quality, such as color distortion, reduced contrast, and noise. Existing underwater image ...

Hyperspectral image (HSI) classification is fundamental to numerous remote sensing applications, enabling detailed analysis of material properties and environmental conditions. Recent Mamba built upon ...

The rapid development of the large language model (LLM) presents huge opportunities for 6G communications – for example, network optimization and management – by allowing users to input task ...

In recent years, the rapid development of the unmanned aerial vehicle (UAV) technology has generated a large number of aerial photography images captured by UAV. Consequently, the object detection in ...

Image fusion facilitates the integration of information from various source images of the same scene into a composite image, thereby benefiting perception, analysis, and understanding. Recently, ...

The availability of unprecedented unsupervised training data, along with neural scaling laws, has resulted in an unprecedented surge in model size and compute requirements for serving/training large ...