Dripta Raychaudhuri

I am an applied scientist at AWS AI where I work on computer vision and machine learning. I completed my PhD from UC Riverside in 2023, where I was advised by Amit K. Roy-Chowdhury. During PhD, I was very fortunate to have interned at Mitsubishi Electric Research Laboratories , NEC Labs, and AWS AI.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  GitHub

profile photo
Updates

  Oct 2023: Paper accepted at IEEE TPAMI

  Oct 2023: Two papers accepted at WACV 2024

  July 2023: Joined AWS AI as an applied scientist!

  July 2023: Two papers accepted at ICCV 2023!

  June 2023: Defended my thesis!

Research

My research is centered around developing algorithms to make machine learning models adaptable to a variety of distributional shifts, encompassing scenarios such as camera viewpoint changes, morphological changes of embodied agents and dynamic computational resource variations, with as minimal supervision as possible.

Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition
Sayak Nag, Dripta S. Raychaudhuri, Sujoy Paul and Amit K. Roy-Chowdhury
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
Prior-guided Source-free Domain Adaptation for Human Pose Estimation
Dripta S. Raychaudhuri, Calvin-Khang Ta, Arindam Dutta, Rohit Lal and Amit K. Roy-Chowdhury
IEEE/CVF International Conference on Computer Vision, 2023
SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets
Cody Simons, Dripta S. Raychaudhuri, Sk Miraj Ahmed, Suya You, Konstantinos Karydis and Amit K. Roy-Chowdhury
IEEE/CVF International Conference on Computer Vision, 2023
Controllable Dynamic Multi-task Architectures
Dripta S. Raychaudhuri, Yumin Suh, Samuel Schulter, Xiang Yu, Masoud Farouki, Amit K. Roy-Chowdhury and Manmohan Chandraker
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022 (Oral)
Cross-domain Imitation from Observations
Dripta S. Raychaudhuri*, Sujoy Paul*, Jeroen van Baar and Amit K. Roy-Chowdhury
(* equal contribution)
International Conference on Machine Learning, 2021 (Long)
Unsupervised Multi-source Domain Adaptation Without Access to Source Data
Sk Miraj Ahmed*, Dripta S. Raychaudhuri*, Sujoy Paul*, Samet Oymak and Amit K. Roy-Chowdhury
(* equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021 (Oral)
Learning Person Re-identification Models from Videos with Weak Supervision
Xueping Wang, Sujoy Paul, Dripta S. Raychaudhuri, Min Liu, Yaonan Wang and Amit K. Roy-Chowdhury
IEEE Transactions on Image Processing, 2021
Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification
Dripta S. Raychaudhuri and Amit K. Roy-Chowdhury
European Conference on Computer Vision, 2020
Channel masking for multivariate time series shapelets
Dripta S. Raychaudhuri, Josif Grabocka and Lars Schmidt-Thieme
arXiv, 2017

Template taken from here