Wide-scale use of visual surveillance in public spaces puts individual
p...
Standard Unsupervised Domain Adaptation (UDA) methods assume the availab...
Object detectors often experience a drop in performance when new
environ...
Object detectors often experience a drop in performance when new
environ...
This paper presents a novel 3D human pose estimation approach using a si...
In this work, we address the problem of estimating the so-called "Social...
Recent years have seen a surge in finding association between faces and
...
The design of an automatic visual inspection system is usually performed...
We investigate and characterize the inherent resilience of conditional
G...
In this work, we address the problem of learning an ensemble of speciali...
Pedestrian attributes, e.g., hair length, clothes type and color, locall...
In this paper, we investigate how to learn rich and robust feature
repre...
Heterogeneous data modalities can provide complementary cues for several...
Diverse input data modalities can provide complementary cues for several...
We propose a guided dropout regularizer for deep networks based on the
e...
Despite the recent deep learning (DL) revolution, kernel machines still
...
In this work, we face the problem of unsupervised domain adaptation with...
Recent works showed that Generative Adversarial Networks (GANs) can be
s...
Regularization for matrix factorization (MF) and approximation problems ...
3D action recognition was shown to benefit from a covariance representat...
Human action recognition from skeletal data is a hot research topic and
...
Domain adaptation techniques address the problem of reducing the sensiti...
Dropout is a very effective way of regularizing neural networks.
Stochas...
Wearable cameras allow people to record their daily activities from a
us...
The emergence of new wearable technologies such as action cameras and
sm...