Cloud-native architecture is becoming increasingly crucial for today's c...
In most urban and suburban areas, pole-like structures such as tree trun...
Autonomous parking (AP) is an emering technique to navigate an intellige...
Neural models with an encoder-decoder framework provide a feasible solut...
Automated Feature Engineering (AFE) refers to automatically generate and...
As one of the most useful online processing techniques, the theta-join
o...
Range-view based LiDAR segmentation methods are attractive for practical...
Realizing human-like perception is a challenge in open driving scenarios...
Uncertainty estimation for unlabeled data is crucial to active learning....
The existing volumetric gain for robotic exploration is calculated in th...
In this paper, we propose an efficient frontier detector method based on...
In this work, we propose the LiDAR Road-Atlas, a compactable and efficie...
Place recognition or loop closure detection is one of the core component...
Although face swapping has attracted much attention in recent years, it
...
Pre-training has been a popular learning paradigm in deep learning era,
...
Cloud computing has been regarded as a successful paradigm for IT indust...
In this paper, we propose a learning-based moving-object tracking method...
Existing imitation learning methods suffer from low efficiency and
gener...
Load balancing is vital for the efficient and long-term operation of clo...
Accurate prediction of short-term OD Matrix (i.e. the distribution of
pa...
Inefficient traffic signal control methods may cause numerous problems, ...
Accurate traffic state prediction is the foundation of transportation co...
Containerization is a lightweight application virtualization technology,...
As a key technology in the 5G era, Mobile Edge Computing (MEC) has devel...
Face swapping has both positive applications such as entertainment,
huma...
To improve the performance of deep learning, mixup has been proposed to ...
Federated learning struggles with their heavy energy footprint on
batter...
Fine-tuning deep neural networks pre-trained on large scale datasets is ...
The development of Internet of Things (IoT) technology enables the rapid...
Transferring knowledge from large source datasets is an effective way to...
Fine-tuning the deep convolution neural network(CNN) using a pre-trained...
The huge success of deep learning in computer vision and natural languag...
Stock price movement prediction is commonly accepted as a very challengi...
Softening labels of training datasets with respect to data representatio...
Cloud Computing paradigm has revolutionized IT industry and be able to o...
This paper was motivated by the problem of how to make robots fuse and
t...