Hi, I am Uday! I am a third year ECE PhD student at Georgia Tech, advised by Prof. Dr. Saibal Mukhopadhyay.
My research interests lie broadly in building computationally efficient, intelligent perception-capable systems. I am also interested in Robot Learning, World Models, and Embodied AI. Currently, I’m working on memory-augmented spatiotemporal representation learning with an application towards event-based perception.
Before starting my Ph.D., I finished my undergraduate in EEE from Bangladesh University of Engineering and Technology (BUET) where I have worked on several research projects related to Computer Vision (small object detection, and segmentation), ML-assisted medical image synthesis, and analysis.
Feel free to reach me at: uday[dot]kamal[at]gatech.edu
News
Jul 17, 2024 | Our work on event-based dense representation with compute efficient adaptive update got accepted in ECCV! |
---|---|
Mar 6, 2023 |
I’ll be joining Amazon Robotics as an Applied Scientiest II intern in |
Jan 20, 2023 | Our work on memory augmented spatiotemporal representation learning got accepted in ICLR (Notable-Top-25%)! |
Sep 15, 2022 | Serving as a reviewer of AAAI-23, ICLR-23, CVPR-23. |
Selected Publications
-
Efficient Learning of Event-based Dense Representation using Hierarchical Memories with Adaptive UpdateAssociative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based PerceptionAnatomy-xnet: An anatomy aware convolutional neural network for thoracic disease classification in chest x-raysDFR-TSD: A deep learning based framework for robust traffic sign detection under challenging weather conditionsDSWE-Net: A deep learning approach for shear wave elastography and lesion segmentation using single push acoustic radiation forceLung cancer tumor region segmentation using recurrent 3d-denseunetApplication of DenseNet in Camera Model Identification and Post-processing Detection.Automatic traffic sign detection and recognition using SegU-Net and a modified Tversky loss function with L1-constraint