Reinforcement Learning (RL) has the potential to surpass human performan...
In the life cycle of highly automated systems operating in an open and
d...
Forecasting future trajectories of agents in complex traffic scenes requ...
Recent work in unsupervised multi-object segmentation shows impressive
r...
Current self-supervised monocular depth estimation methods are mostly ba...
Semantic segmentation methods typically perform per-pixel classification...
In Video Instance Segmentation (VIS), current approaches either focus on...
Predicting future locations of agents in the scene is an important probl...
In self-driving, predicting future in terms of location and motion of al...
While stochastic video prediction models enable future prediction under
...
Most autonomous vehicles are equipped with LiDAR sensors and stereo came...
Self-supervised monocular depth estimation approaches either ignore
inde...
Motion is an important cue for video prediction and often utilized by
se...
Most of the top performing action recognition methods use optical flow a...