Viswanatha Reddy

I'm an SDE at Amazon and passionate about deep learning, LLMs and computer vision. I earned my master's degree from University of Wisconsin-Madison, where I specialized in computer vision and its applications in healthcare. During my master's, I had the privilege of collaborating with Prof. Yin Li's team.

I've contributed to research at Suspect Technologies as a ML Researcher and completed internships at Amazon and Aganitha Cognitive Solutions.

LinkedIn  |  Email  |  CV  |  Scholar  |  Github

News

Research

My primary focus is on computer vision and deep learning, with projects spanning Generative AI, RAG-based workflows, and custom chatbots. I also work on object detection, segmentation, incremental learning, biometrics, and video machine learning. Recent projects include:

RICA2: Rubric-Informed, Calibrated Assessment of Actions

Authors: Abrar Majeedi, Viswanatha Reddy Gajjala, Satya Sai Srinath Namburi GNVV, Yin Li.

ECCV 2024

Incorporates human-designed scoring rubrics for calibrated uncertainty in action quality assessment.

Project Page | arXiv

RICA2 Icon

Detecting Egocentric Actions with ActionFormer

Authors: Chenlin Zhang, Lin Sui, Abrar Majeedi, Viswanatha Reddy Gajjala, Yin Li.

CVPR Workshop 2022

State-of-the-art approach to egocentric action detection.

Report | Code

Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches

Authors: Ayan Kumar Bhunia, Viswanatha Reddy Gajjala, Subhadeep Koley, Rohit Kundu, Aneeshan Sain, Tao Xiang, Yi-Zhe Song.

CVPR 2022

Few-shot incremental learning empowered by user-drawn sketches.

Code | arXiv | Blog

CVPR22 Doodle

Teaching Experience

Other Publications

Professional & Voluntary Work

Served as a reviewer for: