Search Results for author: Abhay Kumar

Found 14 papers, 4 papers with code

Komodo: A Linguistic Expedition into Indonesia's Regional Languages

no code implementations14 Mar 2024 Louis Owen, Vishesh Tripathi, Abhay Kumar, Biddwan Ahmed

However, there remains a significant gap for languages that lack sufficient linguistic resources in the public domain.

[Re] Double Sampling Randomized Smoothing

1 code implementation27 Jun 2023 Aryan Gupta, Sarthak Gupta, Abhay Kumar, Harsh Dugar

This paper is a contribution to the reproducibility challenge in the field of machine learning, specifically addressing the issue of certifying the robustness of neural networks (NNs) against adversarial perturbations.

BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection

1 code implementation15 Jun 2023 Louis Owen, Biddwan Ahmed, Abhay Kumar

The presented methods and benchmarking metrics serve as a valuable resource for future research in OOD detection, enabling further advancements in this field.

Benchmarking Out-of-Distribution Detection +2

Sub-MeV spectroscopy with AstroSat-CZT Imager for Gamma Ray Bursts

no code implementations26 Feb 2021 Tanmoy Chattopadhyay, Soumya Gupta, Vidushi Sharma, Shabnam Iyyani, Ajay Ratheesh, N. P. S. Mithun, E. Aarthy, Sourav Palit, Abhay Kumar, Santosh V Vadawale, A. R. Rao, Varun Bhalerao, Dipankar Bhattacharya

While the 2-pixel Compton scattered events (100 - 300 keV) are used to extract sensitive spectroscopic information, the inclusion of the low-gain pixels (around 20% of the detector plane) after careful calibration extends the energy range of Compton energy spectra to 600 keV.

High Energy Astrophysical Phenomena Instrumentation and Methods for Astrophysics

Exploring Sub-MeV Sensitivity of AstroSat-CZTI for ON-axis Bright Sources

no code implementations26 Feb 2021 Abhay Kumar, Tanmoy Chattopadhyay, Santosh V Vadawale, A. R. Rao, Soumya Gupta, Mithun N. P. S., Varun Bhalerao, Dipankar Bhattacharya

Here we explore the possibility of using the Compton events as well as the low gain pixels to extend the spectroscopic energy range of CZTI for ON-axis bright X-ray sources.

Instrumentation and Methods for Astrophysics High Energy Astrophysical Phenomena


no code implementations25 Sep 2019 Suraj Tripathi, Chirag Singh, Abhay Kumar

And our proposed decoder network serves the purpose of reducing the transformation present in the input image by learning to construct a representative image of the input image class.

Decoder Representation Learning +1

MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation

no code implementations23 Aug 2019 Abhay Kumar, Nishant Jain, Suraj Tripathi, Chirag Singh, Kamal Krishna

The auxiliary task helps in capturing the relevant scale-related information to improve the performance of the main task.

Data Augmentation Density Estimation +1

Learning Discriminative features using Center Loss and Reconstruction as Regularizer for Speech Emotion Recognition

no code implementations19 Jun 2019 Suraj Tripathi, Abhiram Ramesh, Abhay Kumar, Chirag Singh, Promod Yenigalla

This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the recognition of emotion in speech.

Metric Learning Speech Emotion Recognition

Visual Context-aware Convolution Filters for Transformation-invariant Neural Network

no code implementations15 Jun 2019 Suraj Tripathi, Abhay Kumar, Chirag Singh

We propose a novel visual context-aware filter generation module which incorporates contextual information present in images into Convolutional Neural Networks (CNNs).

Rotated MNIST

From Fully Supervised to Zero Shot Settings for Twitter Hashtag Recommendation

no code implementations11 Jun 2019 Abhay Kumar, Nishant Jain, Suraj Tripathi, Chirag Singh

To overcome this limitation, we propose a Zero Shot Learning (ZSL) paradigm for predicting unseen hashtag labels by learning the relationship between the semantic space of tweets and the embedding space of hashtag labels.

Zero-Shot Learning

Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition

no code implementations11 Jun 2019 Suraj Tripathi, Abhay Kumar, Abhiram Ramesh, Chirag Singh, Promod Yenigalla

This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech.

Speech Emotion Recognition

Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network

no code implementations30 Mar 2019 Abhay Kumar, Nishant Jain, Chirag Singh, Suraj Tripathi

The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer.

Biconvex Relaxation for Semidefinite Programming in Computer Vision

1 code implementation31 May 2016 Sohil Shah, Abhay Kumar, Carlos Castillo, David Jacobs, Christoph Studer, Tom Goldstein

We propose a general framework to approximately solve large-scale semidefinite problems (SDPs) at low complexity.

Metric Learning

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