Dissertations - M Tech (CS): Recent submissions

  • Neural Machine Translation for Indian Sign Language 
    Moon, Sushant Sharad (Indian Statistical Institute, Kolkata, 2020-07)
    Sign languages being the primary language of the deaf community, researchers from many elds have been working in this domain from the past two decades. Until now, the majority of the work was in Sign Language Recognition. ...
  • View Count Prediction of a Video through Deep Neural Network based Analysis of Subjective Video Attributes 
    Basu, Spandan (Indian Statistical Institute, Kolkata, 2020-07)
    This research work is aimed to design a method for predicting the view count of a video using deep neural network based analysis of subjective video attributes. With more and more companies turning to online video content ...
  • Shape From Shading Problem Using Deep Learning 
    Sarkar, Soumyajit (Indian Statistical Institute, Kolkata, 2020-07)
    Given a single 2D image, our Objective is to pass that image into a Deep Learning Model and get the 3D shape of that image as output. These tasks have received many attentions recently, however, most of this existing ...
  • Natural Language to Structured Query 
    Sirkhel, Soumya (Indian Statistical Institute, Kolkata, 2020-07)
    Intelligent interface, to enhance e cient interactions between user and databases, is the need of many commercial applications. Oftentimes, users are not familiar with how to frame a structured query as they may not be ...
  • Generation of Texture: A Case Study with Steel Microstructure Images 
    Guha, Soumee (Indian Statistical Institute, Kolkata, 2020-07)
    A lot of work has been done on texture generation techniques. Deep learning based image generation techniques have been extremely successful in generating realistic images. Moreover, reaction-di usion systems have also ...
  • A Game of Cops and Robbers in Some Networks 
    Akhtar, Sheikh Shakil (Indian Statistical Institute, Kolkata, 2020-07)
    Cops and Robber games are pursuit-evasion games played on connected graphs. They have been studied extensively and nding the cop number of certain classes of graphs has been one of the major problems in these games. ...
  • Enhancing speed of Gaussian processes 
    Sil, Sanchari (Indian Statistical Institute, Kolkata, 2020-07)
    Gaussian Processes are used in supervised learning. They have been in the world of machine learning for quite some time, dealing with complex data sets where parametric methods fail. While calculating the gaussian ...
  • Supervised Estimation of Dense Optical Flow 
    Gupta, Rishabh (Indian Statistical Institute, Kolkata, 2020-07)
    End-to-end trained Convolutional Neural Network (CNN) have signi cantly advanced the eld of computer vision in recent years, particularly high-level vision problems, because of its strong non-linear tting ability. In ...
  • Online Relay Switching in the presence of Dynamic Obstacles in millimeter wave D2D communication 
    Shukla, Ravi (Indian Statistical Institute, Kolkata, 2020-07)
    With the ever-increasing number of diverse user-equipments (UEs) and their require- ment of high data rate several modi cations have been done on previous wireless technologies leading to the evolution of 5G device to ...
  • PUTTING NEWS ARTICLES IN CONTEXT 
    Gautam, Rahul (Indian Statistical Institute, Kolkata, 2020-07)
    The work of this dissertation has been done along the lines of TREC News Track Background Linking task. The task is, given a news article suggest other news articles that provide context and background to the current ...
  • Multi-Agent Systems: Model-checking in Logics of Protocols 
    Chakraborty, Pinaki (Indian Statistical Institute, Kolkata, 2021-01)
    A multi-agent system can often be described as a protocol based interacting system wherein the information ow, inter-agent communication and agent behavior can be naturally modeled with dynamic and epistemic logics ...
  • Part 1. An Explainer for Information Retrieval Research 
    Saha, Sourav (Indian Statistical Institute, Kolkata, 2020-07)
    This thesis is organised in two parts. First, an explainability in Information retrieval (IR) research where we focus on the performance of the IR models. We present a toolkit I-REX to illustrate the performance and ...
  • Algorithms for Boundary Labeling of Horizontal Line Segments 
    Kurmi, Abhilash (Indian Statistical Institute, Kolkata, 2019-06)
    In boundary labelling problem the target is to labeling a set P of n points in the plane with labels that are aligned to side of the bounding box of P . In this work, we investigate a variant of this problem. In our ...
  • Acyclicity Tests in Classes of Dense Digraphs in Streaming Model 
    Kundu, Madhumita (Indian Statistical Institute, Kolkata, 2020-07)
    Graph is a popular model to represent highly structured data which involves entities who have pairwise relations between them. In many applications, computing graph theoretic properties after modelling the entire dataset ...
  • Intracranial Hemorrhage Detection 
    Ojha, Naveen (Indian Statistical Institute, Kolkata, 2016-07)
    ICH is diagnosed through history, physical examination, and, most commonly, non- contrast CT examination of the brain, which discloses the anatomic bleeding location. Trauma is a common cause. In the absence of trauma, ...
  • Video Summarization using Neural Networks 
    Kumar, Manish (Indian Statistical Institute, Kolkata, 2020-07)
    With the rapid increase in video data, the need for video summarization has increased. it allows us to search and retrieve video data easily. In this work, we have tried to solve the problem of video summary using ...
  • Efficient Automatic Optimization of Neural Network Architecture 
    Pathak, Harsharaj (Indian Statistical Institute, Kolkata, 2020)
    Neural Networks are at the heart of deep Learning Frame works which have yielded excellent results in various complex problem domains. But the design of neural network architecture is a challenging task. Judicious selection ...
  • Evidential Obstacle learning in Millimeter wave D2D communication using Spatial Correlation 
    Ganesan, Harish (Indian Statistical Institute, Kolkata, 2020-07)
    The 5G technology has created a lot of interest recently to support the increasing demand for higher data rates by the user equipments (UEs). The most interesting part of 5G is the use of device to device (D2D) communication, ...
  • Lower Bound of Coin Counting Problem 
    BHADURI, ARITRA (Indian Statistical Institute, Kolkata, 2020-07)
    We have n coins of two weights. We also have a balance scale to measure the weights of the coins. The objective is to find the number of heavy coins with as few measurement as possible. This problem is known as "coin-counting ...
  • Image Restoration of Night Time Hazy Images 
    Chaurasia, Rishabh (Indian Statistical Institute, Kolkata, 2020-09)
    Image restoration is the operation of taking a corrupt/noisy image and estimat- ing the clean, original image. There are various source of noise in image like fog, haze, glow, scattering of light, motion blur and camera ...

Search DSpace


Advanced Search

Browse

My Account