We present C·ASE, an efficient and effective framework that learns
condi...
It is essential yet challenging for future home-assistant robots to
unde...
Part assembly is a typical but challenging task in robotics, where robot...
Perceiving and interacting with 3D articulated objects, such as cabinets...
This paper proposes a method for representation learning of multimodal d...
Perceiving and manipulating 3D articulated objects (e.g., cabinets, door...
In this work, we tackle the problem of category-level online pose tracki...
Self-supervised representation learning is a critical problem in compute...
Localizing the camera in a known indoor environment is a key building bl...
Humans can robustly localize themselves without a map after they get los...
Point cloud is an important 3D data representation widely used in many
e...
Autonomous part assembly is a challenging yet crucial task in 3D compute...
Reflections are very common phenomena in our daily photography, which
di...
The task of classifying X-ray data is a problem of both theoretical and
...
Many different deep networks have been used to approximate, accelerate o...
Image dehazing aims to recover the uncorrupted content from a hazy image...
Image smoothing represents a fundamental component of many disparate com...
Many different deep networks have been used to approximate, accelerate o...
Removing reflection artefacts from a single-image is a problem of both
t...
This paper proposes a deep neural network structure that exploits edge
i...
While invaluable for many computer vision applications, decomposing a na...