Related papers: DMAT: An End-to-End Framework for Joint Atmospheri…

Unmanned aerial vehicle object detection (UAV-OD) has been widely used in various scenarios. However, most existing UAV-OD algorithms rely on manually designed components, which require extensive tuning. End-to-end models that do not depend…

Depth completion and object detection are two crucial tasks often used for aerial 3D mapping, path planning, and collision avoidance of Uncrewed Aerial Vehicles (UAVs). Common solutions include using measurements from a LiDAR sensor;…

Multi-modal 3D object detection is important for reliable perception in robotics and autonomous driving. However, its effectiveness remains limited under adverse weather conditions due to weather-induced distortions and misalignment between…

We study a mismatch between the deep learning recommendation models' flat architecture, common distributed training paradigm and hierarchical data center topology. To address the associated inefficiencies, we propose Disaggregated…

In this technical report, we present the solution developed by our team VIELab-HUST for text recognition through atmospheric turbulence in Track 2.1 of the CVPR 2023 UG$^{2}$+ challenge. Our solution involves an efficient multi-stage…

Metal artifact significantly degrades Computed Tomography (CT) image quality, impeding accurate clinical diagnosis. However, existing deep learning approaches, such as CNN and Transformer, often fail to explicitly capture the directional…

Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice. Typically, additional data sources are utilized to support the training task. In…

Most existing domain adaptation (DA) methods align the features based on the domain feature distributions and ignore aspects related to fog, background and target objects, rendering suboptimal performance. In our DA framework, we retain the…

Turbulence mitigation (TM) is highly ill-posed due to the stochastic nature of atmospheric turbulence. Most methods rely on multiple frames recorded by conventional cameras to capture stable patterns in natural scenarios. However, they…

Many multi-object tracking (MOT) methods follow the framework of "tracking by detection", which associates the target objects-of-interest based on the detection results. However, due to the separate models for detection and association, the…

We present a self-supervised and self-calibrating multi-shot approach to imaging through atmospheric turbulence, called TurbuGAN. Our approach requires no paired training data, adapts itself to the distribution of the turbulence, leverages…

Deployment of efficient and accurate Deep Learning models has long been a challenge in autonomous navigation, particularly for real-time applications on resource-constrained edge devices. Edge devices are limited in computing power and…

Accurate 3D object detection in autonomous driving relies on Bird's Eye View (BEV) perception and effective temporal fusion. However, existing fusion strategies based on convolutional layers or deformable self-attention struggle to model…

Adversarial Machine Learning (AML) represents the ability to disrupt Machine Learning (ML) algorithms through a range of methods that broadly exploit the architecture of deep learning optimisation. This paper presents Distributed…

Precipitation nowcasting is a vital spatio-temporal prediction task for meteorological applications but faces challenges due to the chaotic property of precipitation systems. Existing methods predominantly rely on single-source radar data…

This technical report presents our solution for the CVPR 2026 UG2+ Challenge Track 3: Dynamic Object Segmentation in Turbulence (DOST). We design a training-free multi-signal segmentation pipeline that combines pretrained motion estimation,…

Multi-object tracking (MOT) has important applications in monitoring, logistics, and other fields. This paper develops a real-time multi-object tracking and prediction system in rugged environments. A 3D object detection algorithm based on…

Persistent multi-object tracking (MOT) allows autonomous vehicles to navigate safely in highly dynamic environments. One of the well-known challenges in MOT is object occlusion when an object becomes unobservant for subsequent frames. The…

The prediction of future climate scenarios under anthropogenic forcing is critical to understand climate change and to assess the impact of potentially counter-acting technologies. Machine learning and hybrid techniques for this prediction…

Automated vehicles require an accurate perception of their surroundings for safe and efficient driving. Lidar-based object detection is a widely used method for environment perception, but its performance is significantly affected by…