Action recognition is a key technology for many industrial applications....
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...
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 to collect data on a large scale in a monocular depth
es...
Explaining predictions of deep neural networks (DNNs) is an important an...