no code implementations • 21 Nov 2023 • Shalini Sharma, Angshul Majumdar, Emilie Chouzenoux, Victor Elvira
We call the proposed approach the deep state-space model.
no code implementations • 21 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.
no code implementations • 19 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.
no code implementations • 27 Nov 2021 • Anurag Goel, Angshul Majumdar
In this work we propose a clustering framework based on the paradigm of transform learning.
no code implementations • 27 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.
no code implementations • 9 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.
no code implementations • 9 Nov 2020 • Pooja Gupta, Angshul Majumdar, Emilie Chouzenoux, Giovanni Chierchia
This work proposes a supervised multi-channel time-series learning framework for financial stock trading.
1 code implementation • 9 Nov 2020 • Pooja Gupta, Jyoti Maggu, Angshul Majumdar, Emilie Chouzenoux, Giovanni Chierchia
This work addresses the problem of analyzing multi-channel time series data %.
no code implementations • 2 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).
1 code implementation • 3 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
no code implementations • 11 Dec 2019 • Shikha Singh, Angshul Majumdar
This work follows the approach of multi-label classification for non-intrusive load monitoring (NILM).
no code implementations • 11 Dec 2019 • Jyoti Maggu, Prerna Singh, Angshul Majumdar
In order to accelerate, compressed sensing based techniques have been proposed.
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 11 Dec 2019 • Megha Gupta, Angshul Majumdar
The objective of this work is to improve the accuracy of building demand forecasting.
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 11 Dec 2019 • Anupriya Gogna, Angshul Majumdar
Design of recommender systems aimed at achieving high prediction accuracy is a widely researched area.
no code implementations • 11 Dec 2019 • Jyoti Maggu, Hemant K. Aggarwal, Angshul Majumdar
This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL).
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 11 Dec 2019 • Anupriya Gogna, Angshul Majumdar
Conventionally, autoencoders are unsupervised representation learning tools.
no code implementations • 11 Dec 2019 • Vanika Singhal, Angshul Majumdar
The concept of deep dictionary learning has been recently proposed.
no code implementations • 11 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.
no code implementations • 10 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.
no code implementations • 10 Dec 2019 • Aanchal Mongia, Neha Jhamb, Emilie Chouzenoux, Angshul Majumdar
Latent factor models have been used widely in collaborative filtering based recommender systems.
no code implementations • 10 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.
no code implementations • 17 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.
1 code implementation • 17 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.
no code implementations • 24 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.
no code implementations • 24 Dec 2018 • Kavya Gupta, Brojeshwar Bhowmick, Angshul Majumdar
This work addresses the problem of reconstructing biomedical signals from their lower dimensional projections.
no code implementations • 27 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.
no code implementations • 22 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.
2 code implementations • 7 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.
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.
no code implementations • 8 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.
no code implementations • 22 Dec 2016 • Vanika Singhal, Shikha Singh, Angshul Majumdar
In the final layer one needs to use the label consistent dictionary learning formulation for classification.
no code implementations • 22 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.
no code implementations • 31 Jan 2016 • Snigdha Tariyal, Angshul Majumdar, Richa Singh, Mayank Vatsa
In this work we propose a new deep learning tool called deep dictionary learning.
no code implementations • 24 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).
no code implementations • 7 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.
no code implementations • 22 Mar 2015 • Angshul Majumdar
In this work we address the problem of real-time dynamic MRI reconstruction.
no code implementations • 10 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.
no code implementations • 17 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.