28 citations · 74 across the 12 of their papers we have counts for
12 papers
Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach
Harman Singh, Poorva Garg, Mohit Gupta +7
We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We e…
ImAiR: Airwriting Recognition framework using Image Representation of IMU Signals
Ayush Tripathi, Arnab Kumar Mondal, Lalan Kumar +1
The problem of Airwriting Recognition is focused on identifying letters written by movement of finger in free space. It is a type of gesture recognition where the dictionary corres…
Transformation Coding: Simple Objectives for Equivariant Representations
Mehran Shakerinava, Arnab Kumar Mondal, Siamak Ravanbakhsh
We present a simple non-generative approach to deep representation learning that seeks equivariant deep embedding through simple objectives. In contrast to existing equivariant net…
SCLAiR : Supervised Contrastive Learning for User and Device Independent Airwriting Recognition
Ayush Tripathi, Arnab Kumar Mondal, Lalan Kumar +1
Airwriting Recognition is the problem of identifying letters written in free space with finger movement. It is essentially a specialized case of gesture recognition, wherein the vo…
Spatiotemporal instabilities and pattern formation in systems of diffusively coupled Izhikevich neurons
Argha Mondal, Chittaranjan Hens, Arnab Mondal +1
Neurons are often connected, spatially and temporally, in phenomenal ways that promote wave propagation. Therefore, it is essential to analyze the emergent spatiotemporal patterns…
ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data
Arnab Kumar Mondal, Himanshu Asnani, Parag Singla +1
Clustering single-cell RNA sequence (scRNA-seq) data poses statistical and computational challenges due to their high-dimensionality and data-sparsity, also known as `dropout' even…
RespVAD: Voice Activity Detection via Video-Extracted Respiration Patterns
Arnab Kumar Mondal, Prathosh A. P
Voice Activity Detection (VAD) refers to the task of identification of regions of human speech in digital signals such as audio and video. While VAD is a necessary first step in ma…
To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs
Arnab Kumar Mondal, Himanshu Asnani, Parag Singla +1
Regularized Auto-Encoders (RAEs) form a rich class of neural generative models. They effectively model the joint-distribution between the data and the latent space using an Encoder…
C-MI-GAN : Estimation of Conditional Mutual Information using MinMax formulation
Arnab Kumar Mondal, Arnab Bhattacharya, Sudipto Mukherjee +3
Estimation of information theoretic quantities such as mutual information and its conditional variant has drawn interest in recent times owing to their multifaceted applications. N…
MaskAAE: Latent space optimization for Adversarial Auto-Encoders
Arnab Kumar Mondal, Sankalan Pal Chowdhury, Aravind Jayendran +3
The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode c…
Revisiting CycleGAN for semi-supervised segmentation
Arnab Kumar Mondal, Aniket Agarwal, Jose Dolz +1
In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotat…
Low Cost Autonomous Navigation and Control of a Mechanically Balanced Bicycle with Dual Locomotion Mode
Ayush Pandey, Subhamoy Mahajan, Adarsh Kosta +17
On the lines of the huge and varied efforts in the field of automation with respect to technology development and innovation of vehicles to make them run autonomously, this paper p…