no code implementations • 20 Jul 2022 • Hongjiang Li, Huanyi Shui, Alemayehu Admasu, Praveen Narayanan, Devesh Upadhyay
Image classification with deep neural networks has seen a surge of technological breakthroughs with promising applications in areas such as face recognition, medical imaging, and autonomous driving.
no code implementations • ICCV 2021 • Yunfei Long, Daniel Morris, Xiaoming Liu, Marcos Castro, Punarjay Chakravarty, Praveen Narayanan
A distinctive feature of Doppler radar is the measurement of velocity in the radial direction for radar points.
no code implementations • CVPR 2021 • Yunfei Long, Daniel Morris, Xiaoming Liu, Marcos Castro, Punarjay Chakravarty, Praveen Narayanan
Here we propose a radar-to-pixel association stage which learns a mapping from radar returns to pixels.
no code implementations • 25 Jan 2020 • Nikita Jaipuria, Shubh Gupta, Praveen Narayanan, Vidya N. Murali
Generative Adversarial Networks (GANs) are now widely used for photo-realistic image synthesis.
no code implementations • 15 Jul 2019 • Praveen Narayanan, Punarjay Chakravarty, Francois Charette, Gint Puskorius
Our seq2seq architecture makes use of a hierarchical encoder to summarize input audio frames.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
no code implementations • 6 Feb 2019 • Punarjay Chakravarty, Praveen Narayanan, Tom Roussel
We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot.
4 code implementations • 17 May 2018 • Rajan Walia, Jacques Carette, Praveen Narayanan, Chung-chieh Shan, Sam Tobin-Hochstadt
They are algorithms whose idiomatic expression requires random array variables that are latent or whose likelihood is conjugate.
Programming Languages Probability