meghshukla
Computer Vision Ph.D. Student @vita-epfl | ex-Research Engineer, MBUX Interior Assist, Mercedes-Benz
Ecole Polytechnique Federale De LausanneLausanne, Switzerland
Pinned Repositories
ActiveLearningForHumanPose
Author implementations for VL4Pose, EGL++ and LearningLoss++, and "unofficial" implementations of various active learning algorithms for human pose estimation!
Atmega-2560-code-Embedded-C
Programming of Firebird V Hardware development platform with Atmega 2560 Microcontroller.
CUDA-Python-GPU-Acceleration-MaximumLikelihood-RelaxationLabelling
GUI implementation with CUDA kernels and Numba to facilitate parallel execution of Maximum Likelihood and Relaxation Labelling algorithms in Python 3
Data-PreProcessing-ML-Python-3
Processing Data with class imbalances, missing values for Machine Learning applications. Use of cross-validation and it's limitations
Fully-Connected-Neural-Network-in-Python-3
Neural Network coded from scratch, only library used is numpy; implemented as a part of my BE project.
LEt-SNE
Dimensionality Reduction and visualization technique that compensates for the curse of dimensionality (ICASSP '20)
meghshukla.github.io
A beautiful portfolio Jekyll theme that works with GitHub Pages.
MPII-Human-Pose-Visualization
Loading and Visualizing MPII Human Pose dataset in Python
Principal-Component-Analysis-Matlab
Principal Component as a tool for Dimensionality Reduction using Hyperspectral images
TIC-TAC
[ICML 2024] Code repository for "TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression". We address the problem of sub-optimal covariance estimation in deep heteroscedastic regression by proposing a new model and metric.
meghshukla's Repositories
meghshukla/MPII-Human-Pose-Visualization
Loading and Visualizing MPII Human Pose dataset in Python
meghshukla/ActiveLearningForHumanPose
Author implementations for VL4Pose, EGL++ and LearningLoss++, and "unofficial" implementations of various active learning algorithms for human pose estimation!
meghshukla/Principal-Component-Analysis-Matlab
Principal Component as a tool for Dimensionality Reduction using Hyperspectral images
meghshukla/LEt-SNE
Dimensionality Reduction and visualization technique that compensates for the curse of dimensionality (ICASSP '20)
meghshukla/Atmega-2560-code-Embedded-C
Programming of Firebird V Hardware development platform with Atmega 2560 Microcontroller.
meghshukla/meghshukla.github.io
A beautiful portfolio Jekyll theme that works with GitHub Pages.
meghshukla/CUDA-Python-GPU-Acceleration-MaximumLikelihood-RelaxationLabelling
GUI implementation with CUDA kernels and Numba to facilitate parallel execution of Maximum Likelihood and Relaxation Labelling algorithms in Python 3
meghshukla/Data-PreProcessing-ML-Python-3
Processing Data with class imbalances, missing values for Machine Learning applications. Use of cross-validation and it's limitations
meghshukla/Fully-Connected-Neural-Network-in-Python-3
Neural Network coded from scratch, only library used is numpy; implemented as a part of my BE project.
meghshukla/KeypointDemo_WADLA_IIIT
Jupyter notebook visualization of 2D single person human pose estimation.
meghshukla/TIC-TAC
Code repository for "TIC-TAC: How To Learn And Evaluate Your Covariance". We derive the TIC: Taylor Induced Covariance and show that incorporating the gradient and curvature results in better covariance predictions. We also propose TAC: Task Agnostic Correlations, a new metric to quantitatively evaluate the covariance.