Megh Shukla

Edit profile

megh.shukla@epfl.ch +41 21 693 73 33 https://meghshukla.github.io/

Google Scholar ID

Linkedin ID

EPFL ENAC IIC VITA
GC C1 392 (Bâtiment GC)
Station 18
1015 Lausanne

+41 21 693 73 33
Office: GC C1 392
EPFL > ENAC > IIC > VITA

Web site: Web site: https://vita.epfl.ch/

EPFL > ETU > EDOC > EDEE

vCard

Publications

Infoscience publications

MotionMap: Representing Multimodality in Human Pose Forecasting

R. Hosseininejad; M. Shukla; S. Saadatnejad; M. Salzmann; A. Alahi

2025. IEEE Conference on Computer Vision and Pattern Recognition, Nashville, Tennessee, USA, 2025-06-11 - 2025-06-15. DOI : 10.1109/cvpr52734.2025.02112.

Detailed record

View at publisher

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

M. Shukla; A. Shameem; M. Salzmann; A. Alahi

2025. 13th International Conference on Learning Representations (ICLR 2025), Singapore, 2025-04-24 - 2025-04-28.

Detailed record

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

M. Shukla; M. Salzmann; A. Alahi

2024. 41st International Conference on Machine Learning (ICML) 2024, Vienna, Austria, July 21-27, 2024.

Detailed record

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

M. Shukla; R. Roy; P. Singh; S. Ahmed; A. Alahi

2022. 33rd British Machine Vision Conference (BMVC 2022), London, UK, November 21-24, 2022.

Detailed record

Megh Shukla

Publications

Infoscience publications

MotionMap: Representing Multimodality in Human Pose Forecasting

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

All postal addresses and positions