Rama Chellappa
Rama Chellappa researches computer vision with collaborators, including face verification and learning-based image restoration. Chellappa, Jun-Cheng Chen, and Vishal M. Patel released Unconstrained Face Verification Using Deep CNN Features in August 2015. The shared study uses convolutional features and evaluates its method on the IARPA Janus Benchmark A dataset. Chellappa, Boyu Lu, and Jun-Cheng Chen co-authored Unsupervised Domain-Specific Deblurring via Disentangled Representations, accepted at CVPR 2019. The method separates image content and blur features and supports training with unpaired data.
- Now at
- Johns Hopkins University
- Works
- 1,358
- Citations
- 71,613
- h-index
- 119
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
2015
Unconstrained face verification
Chellappa, Jun-Cheng Chen, and Vishal M. Patel released Unconstrained Face Verification Using Deep CNN Features in August 2015. The shared study uses convolutional features and evaluates its method on the IARPA Janus Benchmark A dataset.
-
2015
Research recognition
AAAI elected Rama Chellappa as a Fellow in 2015.
-
2019
Unsupervised image deblurring
Chellappa, Boyu Lu, and Jun-Cheng Chen co-authored Unsupervised Domain-Specific Deblurring via Disentangled Representations, accepted at CVPR 2019. The method separates image content and blur features and supports training with unpaired data.
-
2020
Adversarial robustness research
Chellappa co-authored Dual Manifold Adversarial Robustness with Wei-An Lin, Chun Pong Lau, Alexander Levine, and Soheil Feizi. The September 2020 study combines latent-space and image-space perturbations in adversarial training and evaluates specific attack types.
Sources and credits
Photo: umiacs.umd.edu; Rama Chellappa | University of Maryland Institute for Advanced Computer Studies; creator not stated. License: Not stated by source. Source: umiacs.umd.edu. Cropped to a square and resized. Ask us to remove or replace this photo.