Hierarchical reinforcement learning (HRL) has the potential to solve com...
Hierarchical reinforcement learning is a promising approach that uses
te...
In this work, we address the problem of generating speech from silent li...
In this paper, we explore an interesting question of what can be obtaine...
Bias mitigation in machine learning models is imperative, yet challengin...
A wide variety of methods have been developed to enable lifelong learnin...
This paper proposes a video editor based on OpenShot with several
state-...
Normalizing flows provide an elegant method for obtaining tractable dens...
This work studies the long-standing problems of model capacity and negat...
Generative adversarial networks (GANs) are very popular to generate real...
Adaptation of a classifier to new domains is one of the challenging prob...
Understanding unsupervised domain adaptation has been an important task ...
Deep learning models generally learn the biases present in the training ...
There have been a number of techniques that have demonstrated the genera...
Deep learning models suffer from catastrophic forgetting when trained in...
Unsupervised Domain adaptation methods solve the adaptation problem for ...
One of the major limitations of deep learning models is that they face
c...
In this paper, we address the task of improving pair-wise machine transl...
Learning from a few examples is an important practical aspect of trainin...
The ability to envisage the visual of a talking face based just on heari...
Understanding the relationship between the auditory and visual signals i...
Hatching is a common method used by artists to accentuate the third dime...
We present a determinantal point process (DPP) inspired alternative to
n...
Indian language machine translation performance is hampered due to the l...
We present sentence aligned parallel corpora across 10 Indian Languages ...
Convolutional Neural Networks (CNNs) have been successfully applied for
...
In this paper, we propose an approach to improve few-shot classification...
This work presents a novel training technique for deep neural networks t...
In this paper, we solve for the problem of generalized zero-shot learnin...
Generating natural questions from an image is a semantic task that requi...
In this paper, we propose a method to obtain robust explanations for vis...
We present a filter pruning approach for deep model compression, using a...
Researchers have proposed various activation functions. These activation...
In this paper, we propose a method for obtaining sentence-level embeddin...
In this paper, we consider the problem of solving semantic tasks such as...
In this work, we propose a modeling technique for jointly training image...
In this paper, we aim to obtain improved attention for a visual question...
Line art is arguably one of the fundamental and versatile modes of
expre...
In order to successfully perform tasks specified by natural language
ins...
Vision and language tasks have benefited from attention. There have been...
In this paper, we propose a probabilistic framework for solving the task...
Understanding and explaining deep learning models is an imperative task....
We present a simple, yet effective, Neural Machine Translation system fo...
Domain adaptation is essential to enable wide usage of deep learning bas...
In this paper, we aim to solve for unsupervised domain adaptation of
cla...
Recent advances in reinforcement learning have proved that given an
envi...
While convolutional neural networks (CNN) have achieved impressive
perfo...
Abnormal activity recognition requires detection of occurrence of anomal...
In this paper, we solve the problem of adapting classifiers across domai...
This document describes the machine translation system used in the
submi...