I completed my B.Tech (with Honors) in ECE from IIIT-Delhi. In my Bachelor’s Thesis under Dr. Saket Anand in collaboration with Dr. Pavan Turaga, Geometric Media Lab (Arizona State Univesity, USA) at the Infosys Center of Artificial Intelligence, I worked on unsupervised representation learning for disentangling multiple factors of variation in images. Previously, I worked as an intern at the SUTD Brain Lab under Dr. Nengli Lim on the disentanglement of video sequences using Gaussian processes. I have also worked at Collaborative Robotics Lab (CORAL) and Multirobot Autonomy Lab under Dr. P.B. Sujit on target tracking using deep reinforcement learning.
I am mainly interested in unsupervised (or self-supervised) representation learning for visual data, vision for robotics, and vision and language applications.
If you are interested in research collaboration, please drop me an email.
Sept, 2020 : Attending the British Machine Vision Conference, BMVC 2020.
Sept, 2020 : Will be attending Huawei 5th International Video Intelligence Forum, Dublin 2020 from 7th to 11th Sept.
Sept, 2020 : Attending ICUAS 2020 to present work on Target Tracking using DRL.
August, 2020 : Attending ECCV 2020 to present work on Generative Disentanglement using Gaussian Processes.
August, 2020 : Paper on Visual Disentanglement using Contrastive Learning accepted at Perception Through Structured Generative Models (PTSGM) Workshop, ECCV’20.
July, 2020 : Code for Multi-disentangled-features Gaussian Processes Variational AutoEncoder (MGP-VAE) released.