Dripta Raychaudhuri

I am a third year PhD student in the Video Computing Group (VCG), at the University of California, Riverside, advised by Amit K. Roy-Chowdhury. My research interests include Reinforcement Learning, Deep Learning and Computer Vision.

I completed my undergraduate in ECE from Jadavpur University, India where I worked with Ananda S. Chowdhury on problems related to biomedical image segmentation. During my undergraduate, I received the DAAD-WISE fellowship to spend a summer at Universit├Ąt Hildesheim, where I worked on multivariate time-series classification under the guidance of Lars Schmidt-Thieme.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  GitHub

profile photo

  June 2021: Joined NEC Labs as a research intern.

  May 2021: Paper on domain adaptive imitation learning accepted in ICML 2021 as a long presentation.

  March 2021: Paper on unsupervised domain adaptation accepted in CVPR 2021 as an oral presentation.

  January 2021: Paper on weakly supervised re-ID accepted in IEEE TIP.


My interests lie in the scope of reducing supervision in deep learning systems. Along these lines, my research includes few-shot target re-identification, weakly supervised learning from videos and improving sample efficency in deep reinforcement learning algorithms.

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