Multi-finger grasping relies on high quality training data, which is har...
The study of hand-object interaction requires generating viable grasp po...
Differentiable rendering is an essential operation in modern vision, all...
Tool use requires reasoning about the fit between an object's affordance...
A complete representation of 3D objects requires characterizing the spac...
We combine ideas from shock graph theory with more recent appearance-bas...
Representing 3D shape is a fundamental problem in artificial intelligenc...
Computing object skeletons in natural images is challenging, owing to la...
The computer vision community has witnessed recent advances in scene
cat...
We introduce Appearance-MAT (AMAT), a generalization of the medial axis
...
The role of symmetry in computer vision has waxed and waned in importanc...
We present an approach to labeling short video clips with English verbs ...
We present a system that produces sentential descriptions of video: who ...