High-definition (HD) map provides abundant and precise static environmen...
High-definition (HD) map serves as the essential infrastructure of auton...
Autonomous driving requires a comprehensive understanding of the surroun...
Online lane graph construction is a promising but challenging task in
au...
Motion prediction is highly relevant to the perception of dynamic object...
Increasing investment in computing technologies and the advancements in
...
We present MapTR, a structured end-to-end framework for efficient online...
3D detection based on surround-view camera system is a critical techniqu...
Studying the inherent symmetry of data is of great importance in machine...
In this paper, we propose a conceptually novel, efficient, and fully
con...
Video object detection is a fundamental problem in computer vision and h...
Few-shot learning is a challenging task that aims at training a classifi...
Object detection and instance segmentation are two fundamental computer
...
Convolutional neural networks (CNN) based tracking approaches have shown...
Recent cutting-edge feature aggregation paradigms for video object detec...
Video object segmentation (VOS) aims at pixel-level object tracking give...
Letting a deep network be aware of the quality of its own predictions is...
Neural architecture search (NAS) methods have been proposed to release h...
Long-range dependencies can capture useful contextual information to ben...
Traditional multiple object tracking methods divide the task into two pa...
Neural architecture search (NAS) is an important task in network design,...
We study the problem of unsupervised domain adaptive re-identification
(...
Tactical driving decision making is crucial for autonomous driving syste...
Convolutional neural networks (CNN) based tracking approaches have shown...
The prevalent scene text detection approach follows four sequential step...
While deep convolutional neural networks (CNNs) have shown a great succe...
Face Recognition has been studied for many decades. As opposed to tradit...
Pixel-level labelling tasks, such as semantic segmentation, play a centr...
Learning Mahanalobis distance metrics in a high- dimensional feature spa...