Ketul Shah

Hello!

I am a PhD student at Johns Hopkins University in the department of Electrical and Computer Engineering advised by Prof. Rama Chellappa. My broad research interests lie at the intersection of machine learning, computer vision and computer graphics. My current work is on robust action recognition leveraging videos from multiple viewpoints and using synthetic data.

Previously, I obtained an MS in ECE from University of Maryland, College Park. In previous life, I received a Dual Degree (B.Tech + M.Tech) in Electrical Engineering from Indian Institute of Technology (IIT) Madras, where I worked with Prof. Kaushik Mitra at the Computational Imaging Lab.

Recent News

• Dec 2023: Gave a lecture on generalization across viewpoints in Machine Perception course at JHU.
• June 2023: Started internship at Amazon Just Walk Out with Robert, Jie, Marian, Peng & Mayank.
• May 2023: Presented our work on synthetic data for action recognition at ICRA 2023.
• Feb 2023: Paper accepted at CVPR 2023.
• Jan 2023: Paper accepted at ICRA 2023.
• Oct 2022: Paper accepted at WACV 2023.
• Sep 2022: Paper accepted at NeurIPS 2022.
• June 2021: Started internship at Amazon Rekognition with Kaustav, Arthur, Hao, Joe.

Research Work

	Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training arXiv 2023 PAPER Video unsupervised domain adaptation (UDA) by leveraging CLIP for masked distillation and self-training on target domain data. Arun Reddy, William Paul, Corban Rivera, Ketul Shah, Celso M. de Melo, Rama Chellappa.
	DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics arXiv 2023 PAPER Proposed a general "naturnaless" preserving loss based on projected kurtosis concentration property of natural images. Aniket Roy, Maitreya Suin, Anshul Shah, Ketul Shah, Jiang Liu, Rama Chellappa.
	Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances ICRA 2023 PAPER CODE Released RoCoG-v2 dataset for synthetic-to-real and ground-to-air action recognition, and baselines on these domain shifts. Ketul Shah*, Arun Reddy*, William Paul, Rohita Mocharla, Judy Hoffman, Kapil D. Katyal, Dinesh Manocha, Celso M. de Melo, Rama Chellappa.
	HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions CVPR 2023 PAPER CODE New contrastive learning method by generating positives in latent space for self-supervised skeleton-based action recognition. Anshul Shah, Ketul Shah*, Aniket Roy*, Shlok Kumar Mishra, David Jacobs, Anoop Cherian, Rama Chellappa.
	Cap2Aug: Caption guided Image to Image data Augmentation arXiv 2023 PAPER Generate diverse augmentations using image-to-image diffusion models via captioning. Aniket Roy, Ketul Shah*, Anshul Shah*, Anirban Roy, Rama Chellappa.
	Multi-View Action Recognition using Contrastive Learning WACV 2023 PAPER Improved hardness-aware supervised contrastive learning objective for multi-view action recognition. Ketul Shah, Anshul Shah, Chun Pong Lau, Aniket Roy, Celso M. de Melo, Rama Chellappa.
	FeLMi : Few shot Learning with hard Mixup NeurIPS 2022 PAPER Generate samples using manifold mixup and select hard samples based on uncertainty. Aniket Roy, Anshul Shah, Ketul Shah, Prithviraj Dhar, Anoop Cherian, Rama Chellappa.
	Improved modeling of 3D shapes with multi-view depth maps 3DV 2020 (Oral Presentation) PAPER PROJECT PAGE CODE A novel encoder-decoder generative model for 3D shapes using multi-view depth maps; SOTA results on single view reconstruction and generation. Ketul Shah*, Kamal Gupta*, Susmija Jabbireddy*, Abhinav Shristava, Matthias Zwicker.
	Photorealistic Image Reconstruction from Hybrid Intensity and Event based Sensor arXiv 2018 PAPER Novel method for generating high-frame rate video from a conventional camera and an event sensor. Warp the intensity frames by first estimating scene depth and ego-motion. Prasan A. Shedligeri, Ketul Shah, Dhruv Kumar, Kaushik Mitra.