Rudra PK Poudel
Senior Researcher
Toshiba Research Europe, Cambridge, UK

My research interests lie at the intersection of artificial intelligence and cognitive science. I am particularly interested to discover how we learn and how we see. Can we enable machines to do the same things? To answer these questions I am working in machine learning, computer vision and robotics research. My current research interests include efficient (less supervision and compute) learning in deep neural networks and reinforcement learning.

Links : CV, Google scholar, Github, LinkedIn, Twitter

Fast-SCNN: Fast Semantic Segmentation Network
Rudra PK Poudel, Stephan Liwicki, Roberto Cipolla
In British Machine Vision Conference (BMVC), 2019. [Oral]
[pdf] [Slides] [arXiv]

ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time
Rudra PK Poudel, Ujwal Bonde, Stephan Liwicki, Christopher Zach
In British Machine Vision Conference (BMVC), 2018. [Oral]
[pdf] [Slides] [arXiv] [Code]

Predicting Brain Age with Deep Learning from Raw Imaging Data Results in a Reliable and Heritable Biomarker
James H Cole, Rudra PK Poudel, Dimosthenis Tsagkrasoulis, Matthan WA Caan, Claire Steves, Tim D Spector, Giovanni Montana
In NeuroImage, 2017.
[pdf] [NeuroImage] [arXiv] [MIT Tech Review]

Recurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation
Rudra PK Poudel, Pablo Lamata, Giovanni Montana
In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop, 2016.
[pdf] [arXiv]

A Unified Framework for 3D Hand Tracking
Rudra PK Poudel, Jose AS Fonseca, Jian J Zhang, Hammadi Nait-Charif
In International Symposium on Visual Computing (ISVC), 2013. [Oral]
[pdf] [Demo Video]

Region-Based Skin Color Detection
Rudra PK Poudel, Hammadi Nait-Charif, Jian J Zhang, David Liu
In Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP), 2012. [Oral]
[pdf]