A
Angshul Majumdar
Researcher at Indraprastha Institute of Information Technology
Publications - 360
Citations - 5586
Angshul Majumdar is an academic researcher from Indraprastha Institute of Information Technology. The author has contributed to research in topics: Deep learning & Autoencoder. The author has an hindex of 35, co-authored 335 publications receiving 4434 citations. Previous affiliations of Angshul Majumdar include University of British Columbia & Indian Statistical Institute.
Papers
More filters
Journal ArticleDOI
Hyperspectral Image Denoising Using Spatio-Spectral Total Variation
TL;DR: This letter introduces a hyperspectral denoising algorithm based on spatio-spectral total variation that demonstrates the superiority of the proposed algorithm in terms of peak signal-to-noise ratio, structural similarity, and the visual quality.
Journal ArticleDOI
Detecting Silicone Mask-Based Presentation Attack via Deep Dictionary Learning
TL;DR: This paper introduces the first-of-its-kind silicone mask attack database which contains 130 real and attacked videos to facilitate research in developing presentation attack detection algorithms for this challenging scenario.
Journal ArticleDOI
Deep Sparse Coding for Non–Intrusive Load Monitoring
Shikha Singh,Angshul Majumdar +1 more
TL;DR: This paper proposes a deep learning approach to energy disaggregation—instead of learning one level of dictionary, it learns multiple layers of dictionaries for each device, used as a basis for source separation during disaggregation.
Journal ArticleDOI
Deep dictionary learning
TL;DR: It is shown how deeper architectures can be built using the layers of dictionary learning and postulate that the proposed formulation can pave the path for a new class of deep learning tools.
Journal ArticleDOI
AutoImpute: Autoencoder based imputation of single-cell RNA-seq data.
TL;DR: An autoencoder-based sparse gene expression matrix imputation method, which learns the inherent distribution of the input scRNA-seq data and imputes the missing values accordingly with minimal modification to the biologically silent genes.