The recently proposed open-world object and open-set detection achieve a...
Understanding semantic information is an essential step in knowing what ...
Line coverage is to cover linear infrastructure modeled as 1D segments b...
For the 2D laser-based tasks, e.g., people detection and people tracking...
The performance of monocular depth estimation generally depends on the a...
The high performance of RGB-D based road segmentation methods contrasts ...
Edges are the fundamental visual element for discovering tiny obstacles ...
Retrieving occlusion relation among objects in a single image is challen...
Monocular depth prediction is an important task in scene understanding. ...
Occlusion relationship reasoning based on convolution neural networks
co...
Occlusion relationship reasoning demands closed contour to express the
o...
For tiny obstacle discovery in a monocular image, edge is a fundamental
...
Occlusion edge detection requires both accurate locations and context
co...