Deep learning inference brings together the data and the Convolutional N...
We propose SampleDepth, a Convolutional Neural Network (CNN), that is su...
Generative models are becoming ever more powerful, being able to synthes...
Scene flow estimation is a long-standing problem in computer vision, whe...
A triangular mesh is one of the most popular 3D data representations. As...
Video anomaly detection is an ill-posed problem because it relies on man...
The increasing popularity of facial manipulation (Deepfakes) and synthet...
Point cloud registration (PCR) is an important task in many fields inclu...
How many labeled pixels are needed to segment an image, without any prio...
Anomaly detection is a well-established research area that seeks to iden...
Deep learning-based facial recognition (FR) models have demonstrated
sta...
We present a new method for real-time non-rigid dense correspondence bet...
Recently, several deep learning approaches have been proposed for point ...
Deep Neural Networks require large amounts of labeled data for their
tra...
Privacy-Preserving Machine Learning algorithms must balance classificati...
Deep neural networks are prone to adversarial examples that maliciously ...
The search for efficient neural network architectures has gained much fo...
We propose new, and robust, loss functions for the point cloud registrat...
We model local texture patterns using the co-occurrence statistics of pi...
We introduce a binary embedding framework, called Proximity Preserving C...
We present a Deep Image Compression neural network that relies on side
i...
We propose a new method for anomaly detection of human actions. Our meth...
There is a growing number of tasks that work directly on point clouds. A...
The field of self-supervised monocular depth estimation has seen huge
ad...
Processing large point clouds is a challenging task. Therefore, the data...
We consider the problem of segmenting dynamic regions in CrowdCam images...
Underwater images suffer from color distortion and low contrast, because...
We investigate the behavior of convolutional neural networks (CNN) in th...
Co-occurrence Filter (CoF) is a boundary preserving filter. It is based ...
We address the novel problem of detecting dynamic regions in CrowdCam im...
Best-Buddies Tracking (BBT) applies the Best-Buddies Similarity measure ...
We propose a novel method for template matching in unconstrained
environ...
Spatially Coherent Random Forest (SCRF) extends Random Forest to create
...
We propose an algorithm for recovering depth using less than two images....