Megh Shukla

4 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) ❓ The Questioner

Venues

CVPR (1) ICLR (1) ICML (1) WACV (1)

Top co-authors

Mathieu Salzmann (3) Alexandre Alahi (3) Saeed Saadatnejad (1) Reyhaneh Hosseininejad (1) Aziz Shameem (1)

Research topics

Machine Learning (4) Core Methods (3) Learning Types · Machine Learning (3) Computer Vision (2) Analysis (2) Optimization & Theory (2) Artificial Intelligence (1) Deep Learning (1) Mathematics & Optimization (1) Core AI (1) Learning Types · Deep Learning (1) Mathematics (1) Optimization (1)

Keywords

covariance estimation (2) heteroscedastic regression (2) uncertainty quantification (1) self-supervised learning (1) human pose estimation (1) uncertainty estimation (1) multimodal prediction (1) motion prediction (1) human pose forecasting (1) neural network (1) spatial distribution (1) taylor polynomial (1) bayesian uncertainty (1) heatmap representation (1) negative log-likelihood (1) expected gradient length (1) 2-wasserstein distance (1) second-order (1) active learning (1) task agnostic correlations (1)

Papers

MotionMap: Representing Multimodality in Human Pose Forecasting CVPR 2025 Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression ICLR 2025 TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression ICML 2024 Bayesian Uncertainty and Expected Gradient Length - Regression: Two Sides of the Same Coin? WACV 2022