Several recent works have directly extended the image masked autoencoder...
Previous research has studied the task of segmenting cinematic videos in...
Modeling dynamics is often the first step to making a vehicle autonomous...
Contrastive learning has recently narrowed the gap between self-supervis...
Legged robots can traverse a wide variety of terrains, some of which may...
Geometric methods for solving open-world off-road navigation tasks, by
l...
Scenes play a crucial role in breaking the storyline of movies and TV
ep...
Single-view 3D is the task of recovering 3D properties such as depth and...