Search Results for author: Angshul Majumdar

Found 46 papers, 4 papers with code

Synthetic Image Detection: Highlights from the IEEE Video and Image Processing Cup 2022 Student Competition

no code implementations21 Sep 2023 Davide Cozzolino, Koki Nagano, Lucas Thomaz, Angshul Majumdar, Luisa Verdoliva

The Video and Image Processing (VIP) Cup is a student competition that takes place each year at the IEEE International Conference on Image Processing.

Synthetic Image Detection

Graph Regularized Probabilistic Matrix Factorization for Drug-Drug Interactions Prediction

no code implementations19 Oct 2022 Stuti Jain, Emilie Chouzenoux, Kriti Kumar, Angshul Majumdar

The performance of the proposed method is evaluated through the DrugBank dataset, and comparisons are provided against state-of-the-art techniques.

Matrix Completion

Transformed K-means Clustering

no code implementations27 Nov 2021 Anurag Goel, Angshul Majumdar

In this work we propose a clustering framework based on the paradigm of transform learning.

Clustering

Sparse Subspace Clustering Friendly Deep Dictionary Learning for Hyperspectral Image Classification

no code implementations27 Nov 2021 Anurag Goel, Angshul Majumdar

We show that the proposed formulation improves over the state-of-the-art deep learning techniques in hyperspectral image clustering.

Clustering Dictionary Learning +5

DeConFuse : A Deep Convolutional Transform based Unsupervised Fusion Framework

no code implementations9 Nov 2020 Pooja Gupta, Jyoti Maggu, Angshul Majumdar, Emilie Chouzenoux, Giovanni Chierchia

This work proposes an unsupervised fusion framework based on deep convolutional transform learning.

Deep Convolutional Transform Learning -- Extended version

no code implementations2 Oct 2020 Jyoti Maggu, Angshul Majumdar, Emilie Chouzenoux, Giovanni Chierchia

This work introduces a new unsupervised representation learning technique called Deep Convolutional Transform Learning (DCTL).

BIG-bench Machine Learning Clustering +1

A computational approach to aid clinicians in selecting anti-viral drugs for COVID-19 trials

1 code implementation3 Jul 2020 Aanchal Mongia, Sanjay Kr. Saha, Emilie Chouzenoux, Angshul Majumdar

The main contribution of this work is a manually curated database publicly shared, comprising of existing associations between viruses and their corresponding antivirals.

Quantitative Methods

RODEO: Robust DE-aliasing autoencOder for Real-time Medical Image Reconstruction

no code implementations11 Dec 2019 Janki Mehta, Angshul Majumdar

In this work we address the problem of real-time dynamic medical MRI and X Ray CT image reconstruction from parsimonious samples Fourier frequency space for MRI and sinogram tomographic projections for CT. Today the de facto standard for such reconstruction is compressed sensing.

De-aliasing Image Reconstruction

Simultaneous Detection of Multiple Appliances from Smart-meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning

no code implementations11 Dec 2019 Vanika Singhal, Jyoti Maggu, Angshul Majumdar

There are hardly any studies in deep learning based multi label classification; two new deep learning techniques to solve the said problem are fundamental contributions of this work.

Dictionary Learning General Classification +2

Blind Denoising Autoencoder

no code implementations11 Dec 2019 Angshul Majumdar

The term blind denoising refers to the fact that the basis used for denoising is learnt from the noisy sample itself during denoising.

Denoising Dictionary Learning

Semi-supervised Stacked Label Consistent Autoencoder for Reconstruction and Analysis of Biomedical Signals

no code implementations11 Dec 2019 Anupriya Gogna, Angshul Majumdar, Rabab Ward

In this work we propose an autoencoder based framework for simultaneous reconstruction and classification of biomedical signals.

Classification EEG +3

Recurrent Transform Learning

no code implementations11 Dec 2019 Megha Gupta, Angshul Majumdar

The objective of this work is to improve the accuracy of building demand forecasting.

regression

Analysis Co-Sparse Coding for Energy Disaggregation

no code implementations11 Dec 2019 Shikha Singh, Angshul Majumdar

The advantage of our proposed approach is that, the requirement of training volume drastically reduces compared to state-of-the-art techniques.

blind source separation Dictionary Learning

Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification

no code implementations11 Dec 2019 Vanika Singhal, Angshul Majumdar

Most of the prior studies were based on the unsupervised formulation; and in all cases, the training algorithm was greedy and hence sub-optimal.

Classification Dictionary Learning +2

Kernel Transform Learning

no code implementations11 Dec 2019 Jyoti Maggu, Angshul Majumdar

The concept of kernel dictionary learning has been introduced in the recent past, where the dictionary is represented as a linear combination of non-linear version of the data.

Dictionary Learning Representation Learning

Deep Sparse Coding for Non-Intrusive Load Monitoring

no code implementations11 Dec 2019 Shikha Singh, Angshul Majumdar

Prior studies in this area are shallow learning techniques, i. e. they learn a single layer of dictionary for every device.

blind source separation Dictionary Learning +1

Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification

no code implementations11 Dec 2019 Vanika Singhal, Hemant K. Aggarwal, Snigdha Tariyal, Angshul Majumdar

This work proposes a new framework for deep learning that has been particularly tailored for hyperspectral image classification.

Classification Dictionary Learning +2

Transformed Subspace Clustering

no code implementations10 Dec 2019 Jyoti Maggu, Angshul Majumdar, Emilie Chouzenoux

We assume that, even if the raw data is not separable into subspac-es, one can learn a representation (transform coef-ficients) such that the learnt representation is sep-arable into subspaces.

Benchmarking Clustering +1

Reconstructing Multi-echo Magnetic Resonance Images via Structured Deep Dictionary Learning

no code implementations10 Dec 2019 Vanika Singhal, Angshul Majumdar

In recent times, it has been shown that instead of using off-the-shelf CS, better results can be obtained by adaptive reconstruction algorithms based on structured dictionary learning.

Dictionary Learning

Multi Label Restricted Boltzmann Machine for Non-Intrusive Load Monitoring

no code implementations17 Oct 2019 Sagar Verma, Shikha Singh, Angshul Majumdar

Some recent studies have proposed that if we frame Non-Intrusive Load Monitoring (NILM) as a multi-label classification problem, the need for appliance-level data can be avoided.

Multi-Label Classification Non-Intrusive Load Monitoring

Collaborative Filtering with Label Consistent Restricted Boltzmann Machine

1 code implementation17 Oct 2019 Sagar Verma, Prince Patel, Angshul Majumdar

The possibility of employing restricted Boltzmann machine (RBM) for collaborative filtering has been known for about a decade.

Collaborative Filtering Recommendation Systems

Motion Blur removal via Coupled Autoencoder

no code implementations24 Dec 2018 Kavya Gupta, Brojeshwar Bhowmick, Angshul Majumdar

In this work, we propose a new formulation that recasts deblurring as a transfer learning problem, it is solved using the proposed coupled autoencoder.

Deblurring Transfer Learning

Hierarchical Representation Learning for Kinship Verification

no code implementations27 May 2018 Naman Kohli, Mayank Vatsa, Richa Singh, Afzel Noore, Angshul Majumdar

Utilizing the information obtained from the human study, a hierarchical Kinship Verification via Representation Learning (KVRL) framework is utilized to learn the representation of different face regions in an unsupervised manner.

Face Verification Kinship Verification +1

MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis

no code implementations22 Feb 2018 Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa, Angshul Majumdar

The proposed algorithm learns multi-level sparse representation for both high and low resolution gallery images, along with an identity aware dictionary and a transformation function between the two representations for face identification scenarios.

Face Identification Face Recognition +2

Indian Regional Movie Dataset for Recommender Systems

2 code implementations7 Jan 2018 Prerna Agarwal, Richa Verma, Angshul Majumdar

It consists of movies belonging to 18 different Indian regional languages and metadata of users with varying demographics.

Collaborative Filtering Matrix Completion +1

Face Sketch Matching via Coupled Deep Transform Learning

no code implementations ICCV 2017 Shruti Nagpal, Maneet Singh, Richa Singh, Mayank Vatsa, Afzel Noore, Angshul Majumdar

The performance of the proposed models is evaluated on a novel application of sketch-to-sketch matching, along with sketch-to-digital photo matching.

Face Recognition

Gender and Ethnicity Classification of Iris Images using Deep Class-Encoder

no code implementations8 Oct 2017 Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh, Afzel Noore, Angshul Majumdar

Soft biometric modalities have shown their utility in different applications including reducing the search space significantly.

Gender Classification General Classification

How to Train Your Deep Neural Network with Dictionary Learning

no code implementations22 Dec 2016 Vanika Singhal, Shikha Singh, Angshul Majumdar

In the final layer one needs to use the label consistent dictionary learning formulation for classification.

Age And Gender Classification Dictionary Learning +2

Deep Blind Compressed Sensing

no code implementations22 Dec 2016 Shikha Singh, Vanika Singhal, Angshul Majumdar

In this work we show that by learning directly from the compressed domain, considerably better results can be obtained.

Greedy Deep Dictionary Learning

no code implementations31 Jan 2016 Snigdha Tariyal, Angshul Majumdar, Richa Singh, Mayank Vatsa

In this work we propose a new deep learning tool called deep dictionary learning.

Dictionary Learning

Fast Acquisition for Quantitative MRI Maps: Sparse Recovery from Non-linear Measurements

no code implementations24 Dec 2015 Anupriya Gogna, Angshul Majumdar

Our simulation results show that our method yields very accurate and robust results from only two partially sampled scans (total scan time being the same as a single echo MRI).

Blind Compressive Sensing Framework for Collaborative Filtering

no code implementations7 May 2015 Anupriya Gogna, Angshul Majumdar

Existing works based on latent factor models have focused on representing the rating matrix as a product of user and item latent factor matrices, both being dense.

Collaborative Filtering Compressive Sensing

Extension of Sparse Randomized Kaczmarz Algorithm for Multiple Measurement Vectors

no code implementations10 Jan 2014 Hemant Kumar Aggarwal, Angshul Majumdar

Recently an algorithm for finding sparse solution to a linear system of equations has been proposed based on weighted randomized Kaczmarz algorithm.

Face Recognition Fairness

Matrix recovery using Split Bregman

no code implementations17 Dec 2013 Anupriya Gogna, Ankita Shukla, Angshul Majumdar

The use of Bregman technique improves the convergence speed of our algorithm and gives a higher success rate.

Recommendation Systems Video Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.