Precision and Recall are two prominent metrics of generative performance...
Due to data's unavailability or large size, and the high computational a...
With recent progress in deep generative models, the problem of identifyi...
The growing number of adversarial attacks in recent years gives attacker...
In this paper, we introduce a novel non-linear activation function that
...
Research in media forensics has gained traction to combat the spread of
...
The ability to capture complex linguistic structures and long-term
depen...
Fake news often involves semantic manipulations across modalities such a...
Robust speaker recognition, including in the presence of malicious attac...
The current spike of hyper-realistic faces artificially generated using
...
Fingerprint presentation attack detection is becoming an increasingly
ch...
In this work, we present a general framework for building a biometrics s...
Supervised machine learning models often associate irrelevant nuisance
f...
We propose a novel approach to achieving invariance for deep neural netw...
Face segmentation is the task of densely labeling pixels on the face
acc...
Face occlusions, covering either the majority or discriminative parts of...
We present a unified invariance framework for supervised neural networks...
The spread of misinformation through synthetically generated yet realist...
Spread of misinformation has become a significant problem, raising the
i...
For enterprise, personal and societal applications, there is now an
incr...
Image repurposing is a commonly used method for spreading misinformation...
Data representations that contain all the information about target varia...
Nefarious actors on social media and other platforms often spread rumors...
Recently, generative adversarial networks and adversarial autoencoders h...
We present Generative Adversarial Capsule Network (CapsuleGAN), a framew...
Conditional variants of Generative Adversarial Networks (GANs), known as...
Real world multimedia data is often composed of multiple modalities such...
Image splicing is a very common image manipulation technique that is
som...
We introduce our method and system for face recognition using multiple
p...
In this paper we present a fully trainable binarization solution for deg...