Generalizing models trained on normal visual conditions to target domain...
Unsupervised domain adaptation has recently emerged as an effective para...
Self-training has greatly facilitated domain adaptive semantic segmentat...
Domain adaptive semantic segmentation refers to making predictions on a
...
Real-world training data usually exhibits long-tailed distribution, wher...
Current methods for trajectory prediction operate in supervised manners,...
Omnidirectional 360 camera proliferates rapidly for autonomous robots
si...
Depth Completion deals with the problem of converting a sparse depth map...
In this paper, we make the first attempt to build a framework to
simulta...
Depth prediction is one of the fundamental problems in computer vision. ...
We aim to enable a mobile robot to navigate through environments with de...
Depth estimation from a single image is a fundamental problem in compute...
Navigation is an essential capability for mobile robots. In this paper, ...
Scene parsing aims to assign a class (semantic) label for each pixel in ...