Warning: this paper contains content that may be inappropriate or offens...
Scaling up weakly-supervised datasets has shown to be highly effective i...
Despite improvements to the generalization performance of automated spee...
Action in video usually involves the interaction of human with objects.
...
Deep neural networks have largely demonstrated their ability to perform
...
Modern Automatic Speech Recognition (ASR) systems often use a portfolio ...
Traditionally, research in automated speech recognition has focused on
l...
Classification algorithms in machine learning often assume a flat label
...
Multi-modal machine learning (ML) models can process data in multiple
mo...
Multimodal ML models can process data in multiple modalities (e.g., vide...
Object detection models shipped with camera-equipped mobile devices cann...
Lifelong learning, the problem of continual learning where tasks arrive ...
Deep neural networks (DNNs) often suffer from "catastrophic forgetting"
...
The key challenge of generative Visual Dialogue (VD) systems is to respo...
In this paper, we present a novel approach for the task of eXplainable
Q...
State-of-the-art deep model compression methods exploit the low-rank
app...
We study the problem of data release with privacy, where data is made
av...
Stream deinterleaving is an important problem with various applications ...
We propose Trusted Neural Network (TNN) models, which are deep neural ne...
We present a novel framework for domain adaptation, whereby both geometr...
Documents exhibit sequential structure at multiple levels of abstraction...
In this paper, we address the problem of real-time detection of viruses
...