We propose a novel zero-shot approach to computing correspondences betwe...
Modern deep neural networks are prone to being overconfident despite the...
Optical flow is a regression task where convolutional neural networks (C...
The focus in deep learning research has been mostly to push the limits o...
Thermal Infrared (TIR) cameras are gaining popularity in many computer v...
Generally, convolutional neural networks (CNNs) process data on a regula...
In most computer vision applications, convolutional neural networks (CNN...