The excellent performance of Transformer in supervised learning has led ...
Visual explanation is an approach for visualizing the grounds of judgmen...
3D object detection has become indispensable in the field of autonomous
...
In orthogonal world coordinates, a Manhattan world lying along cuboid
bu...
While convolutional neural networks (CNNs) have achieved excellent
perfo...
Data augmentation is an essential technique for improving recognition
ac...
In object detection, data amount and cost are a trade-off, and collectin...
Robot navigation with deep reinforcement learning (RL) achieves higher
p...
Color images are easy to understand visually and can acquire a great dea...
In action understanding in indoor, we have to recognize human pose and a...
Although recent learning-based calibration methods can predict extrinsic...
It is difficult for people to interpret the decision-making in the infer...
It is difficult to collect data on a large scale in a monocular depth
es...
Mutual learning, in which multiple networks learn by sharing their knowl...
Deep reinforcement learning (DRL) has great potential for acquiring the
...
Placing objects is a fundamental task for domestic service robots (DSRs)...
Domestic service robots (DSRs) are a promising solution to the shortage ...
We propose Deep Collaborative Learning (DCL), which is a method that
inc...
Human-in-the-loop (HITL), which introduces human knowledge to machine
le...
Visual explanation enables human to understand the decision making of De...
Path prediction is a fundamental task for estimating how pedestrians or
...
This paper proposes a novel type of random forests called a denoising ra...
Recent trends show recognition accuracy increasing even more profoundly....