We introduce RotateIt, a system that enables fingertip-based object rota...
We exploit the complementary strengths of vision and proprioception to
a...
This work attempts to provide a plausible theoretical framework that aim...
This work attempts to interpret modern deep (convolutional) networks fro...
Learning long-term dynamics models is the key to understanding physical
...
Facial image retrieval plays a significant role in forensic investigatio...
Initialization, normalization, and skip connections are believed to be t...
We present a simple yet effective end-to-end trainable deep network with...
In this paper, we propose a method to obtain a compact and accurate 3D
w...
We present a conceptually simple yet effective algorithm to detect wiref...
Convolutional neural networks (CNNs) are inherently limited to model
geo...
We present the first fully convolutional end-to-end solution for
instanc...