The biometric systems are widely deployed in various sectors for authentication purposes– India’s Aadhaar project (a multi-biometric database of above 1.3 billion of India’s population) being the prominent example. The ...
Malware Detection is an important problem in modern day due to the increasing frequency
of malware attacks using unknown malware strains. Unlike traditional detection techniques
which require a signature for each sample, ...
Taboo is prohibition or restriction by social custom. So generally teaching a taboo topic
is not easy for a teacher as well a student might feel hesitated to ask doubts for the taboo
topics.We aim to study can VR help ...
We consider a generalization of the classical K-center problem with capacities, demands, and
outliers. The capacitated K-center problem adds a constraint to the original K-center problem
of every vertex having a capacity ...
Saini, Vipul; Mutharaju, V. Raghava (advisor); Chakraborty, Tanmoy (advisor)(IIIT-Delhi, 2020-06-05)
Knowledge graphs have become quite popular and their utility is increasing at a very fast rate.
There exist numerous extensive knowledge graphs that contain information on a plethora of
topics. With new information ...
The shepherding problem is a problem setting in the multi-agent systems domain. The primary
aim is to guide or ‘shepherd’ a swarm of unwilling agents to a destination, with the help of autonomous agents. We explore this ...
Traditionally, algorithms try to find the optimal solution for a problem in a “three-phase”
approach: fetch the input, run the algorithm, output the solution. But recently, there has been
an interest in understanding ...
We address the problem of finding a textual summary of facts within a path in a knowledge
graph.Knowledge graphs are increasingly used in search engines and store data in the form of
a Semantic Web structure making ...
Social media has now become the most popular medium for self-expression and
community building. More and more people are turning to it to express, write, vent or
just be while being comfortable doing so because it’s an ...
Using the publicly available data-sets and the surveys, we aim to design a web-portal that
would be able to provide insights into venues that are considered important for research as well
as information of researchers ...
Community affiliation of a node plays an important role in determining its contextual position in
the network, which may raise privacy concerns when a sensitive node wants to hide its identity
in a network. Oftentimes, ...
Approximate Reasoning involves compromising the soundness or the completeness of reasoning
over description logic ontologies in favor of significant speed up in the run time. The efficiency
of approximate Reasoning can ...
Modality refers to how something happens or is experienced. It is the representation
format in which information is stored. Multimodal Learning involves relating information
from multiple sources. Many modalities are ...
We use Mean Shift clustering in the latent space of an auto-encoder to have a better representation of the data and a more structured latent space. Instead of just using the mode of the
distribution calculated using kernel ...
Jain, Kshitiz; Priysha; Subramanyam, AV (advisor)(IIIT-Delhi, 2020-05-28)
Subspace learning has often been explored for various applications such as dimensionality reduction,
denoising, clustering and feature extraction among others. However, low rank subspace learning for
clustering as well ...
Transfer learning is widely used for many applications, but it is difficult to adapt intermediate layers of
the network to a new learning task with less data available. Learning the importance that key connections play ...
Convolutional Neural Networks are trained using a gradient descent back propagation technique
which trains weights in each layer for the sole goal of minimizing training error. Hence, the
resulting weights cannot be ...
Monitoring of protected areas to curb illegal activities like poaching and animal trafficking is a
monumental task. To augment existing manual patrolling efforts, unmanned aerial surveillance
using visible and thermal ...
The non-intrusive nature and high accuracy of face recognition algorithms have led to their successful deployment across multiple applications ranging from border access to mobile unlocking
and digital payments. However, ...
Ontology Learning is the semi-automatic and automatic extraction of ontology from a natural
language text, using text-mining and information extraction. Each ontology primarily represents
some concepts and their corresponding ...