Related papers: SGDViT: Saliency-Guided Dynamic Vision Transformer…

With the rapid growth of the low-altitude economy, UAVs have become crucial for measurement and tracking in patrol systems. However, in GNSS-denied areas, satellite-based localization methods are prone to failure. This paper presents a…

Saliency computation models aim to imitate the attention mechanism in the human visual system. The application of deep neural networks for saliency prediction has led to a drastic improvement over the last few years. However, deep models…

This paper presents a visual tracking system that is capable or running real time on-board a small UAV (Unmanned Aerial Vehicle). The tracking system is computationally efficient and invariant to lighting changes and rotation of the object…

Operator learning, which aims to approximate maps between infinite-dimensional function spaces, is an important area in scientific machine learning with applications across various physical domains. Here we introduce the Continuous Vision…

In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…

Multiple object tracking (MOT) in Unmanned Aerial Vehicle (UAV) videos is important for diverse applications in computer vision. Current MOT trackers rely on accurate object detection results and precise matching of target reidentification…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

UAV-ground visual tracking (UGVT) aims to simultaneously track the same object from both the UAV and the ground view. However, existing two-stream methods suffer from isolated feature extraction and rely heavily on implicit appearance…

Navigating dynamic environments requires the robot to generate collision-free trajectories and actively avoid moving obstacles. Most previous works designed path planning algorithms based on one single map representation, such as the…

We introduce the Visual Implicit Geometry Transformer (ViGT), an autonomous driving geometric model that estimates continuous 3D occupancy fields from surround-view camera rigs. ViGT represents a step towards foundational geometric models…

Visual object tracking is a fundamental component of transportation systems, especially for intelligent driving. Despite achieving state-of-the-art performance in visual tracking, recent single-branch trackers tend to overlook the weak…

Occlusion is a longstanding difficulty that challenges the UAV-based object detection. Many works address this problem by adapting the detection model. However, few of them exploit that the UAV could fundamentally improve detection…

Accurate detection of Unmanned Aerial Vehicles (UAVs) is critical for surveillance, security, and airspace monitoring. However, existing datasets remain limited in scale, resolution, and the ability to capture objects across extreme size…

Visual active tracking is a growing research topic in robotics due to its key role in applications such as human assistance, disaster recovery, and surveillance. In contrast to passive tracking, active tracking approaches combine vision and…

Detecting objects from UAV-captured images is challenging due to the small object size. In this work, a simple and efficient adaptive zoom-in framework is explored for object detection on UAV images. The main motivation is that the…

User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions and low-level agent actions. While recent advancements in…

Depth estimation has been widely studied and serves as the fundamental step of 3D perception for robotics and autonomous driving. Though significant progress has been made in monocular depth estimation in the past decades, these attempts…

We propose an online visual tracking algorithm by learning discriminative saliency map using Convolutional Neural Network (CNN). Given a CNN pre-trained on a large-scale image repository in offline, our algorithm takes outputs from hidden…

Accurate perception of dynamic obstacles is essential for autonomous robot navigation in indoor environments. Although sophisticated 3D object detection and tracking methods have been investigated and developed thoroughly in the fields of…

For 3D object detection, both camera and lidar have been demonstrated to be useful sensory devices for providing complementary information about the same scenery with data representations in different modalities, e.g., 2D RGB image vs 3D…