Neural network-based recent research developments in SLAM for autonomous ground vehicles: A review
The development of autonomous vehicles has prompted an interest in exploring various
techniques in navigation. One such technique is simultaneous localization and mapping …
techniques in navigation. One such technique is simultaneous localization and mapping …
Learning graph neural networks for image style transfer
State-of-the-art parametric and non-parametric style transfer approaches are prone to either
distorted local style patterns due to global statistics alignment, or unpleasing artifacts …
distorted local style patterns due to global statistics alignment, or unpleasing artifacts …
Jperceiver: Joint perception network for depth, pose and layout estimation in driving scenes
Depth estimation, visual odometry (VO), and bird's-eye-view (BEV) scene layout estimation
present three critical tasks for driving scene perception, which is fundamental for motion …
present three critical tasks for driving scene perception, which is fundamental for motion …
On robust cross-view consistency in self-supervised monocular depth estimation
Remarkable progress has been made in self-supervised monocular depth estimation (SS-
MDE) by exploring cross-view consistency, eg, photometric consistency and 3D point cloud …
MDE) by exploring cross-view consistency, eg, photometric consistency and 3D point cloud …
D2Animator: Dual Distillation of StyleGAN For High-Resolution Face Animation
The style-based generator architectures (eg StyleGAN v1, v2) largely promote the
controllability and explainability of Generative Adversarial Networks (GANs). Many …
controllability and explainability of Generative Adversarial Networks (GANs). Many …
[PDF][PDF] Efficient representation learning with graph neural networks
Y Jing - 2023 - core.ac.uk
Graph neural networks (GNNs) have emerged as the dominant paradigm for graph
representation learning, igniting widespread interest in utilizing sophisticated GNNs for …
representation learning, igniting widespread interest in utilizing sophisticated GNNs for …
Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning
The problem of deep long-tailed learning, a prevalent challenge in the realm of generic
visual recognition, persists in a multitude of real-world applications. To tackle the heavily …
visual recognition, persists in a multitude of real-world applications. To tackle the heavily …