/Deva Kannan Ramanan

Deva Kannan Ramanan

Portrait of Deva Kannan Ramanan
Associate Professor
Office: 221 Elliot Dunlap Smith Hall
Phone: (412) 268-6966
Personal Homepage
Administrative Assistant: Stephanie Matvey

Mailing Address

My research focuses on computer vision, often motivated by the task of understanding people from visual data. My work tends to make heavy use of machine learning techniques, often using the human visual system as inspiration. For example, temporal processing is a key component of human perception, but is still relatively unexploited in current visual recognition systems. Machine learning from big (visual) data allows systems to learn subtle statistical regularities of the visual world. But humans have the ability to learn from very few examples. Here’s a recent talk (from 2015) that discusses some thoughts on these issues.

Displaying 5 Publications
Photo-Sketching: Inferring Contour Drawings from Images
Mengtian Li, Zhe Lin, Radomír Měch, Ersin Yumer and Deva Ramanan

Conference Paper, WACV, January, 2019
Few-Shot Human Motion Prediction via Meta-learning
Liang-Yan Gui, Yuxiong Wang, Deva Ramanan and Jose M. F. Moura

Conference Paper, European Conference on Computer Vision (ECCV), October, 2018
Learning to Model the Tail
Yuxiong Wang, Deva Kannan Ramanan and Martial Hebert

Conference Paper, 31st Conference on Neural Information Processing Systems (NIPS), December, 2017
Growing a Brain: Fine-Tuning by Increasing Model Capacity
Yuxiong Wang, Deva Ramanan and Martial Hebert

Conference Paper, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), July, 2017

Current Affiliates