P
Prem Natarajan
Researcher at Information Sciences Institute
Publications - 158
Citations - 4057
Prem Natarajan is an academic researcher from Information Sciences Institute. The author has contributed to research in topics: Computer science & Machine translation. The author has an hindex of 29, co-authored 144 publications receiving 3140 citations. Previous affiliations of Prem Natarajan include Raytheon & Amazon.com.
Papers
More filters
Proceedings ArticleDOI
Deep Face Recognition: A Survey
TL;DR: The survey provides a clear, structured presentation of the principal, state-of-the-art (SOTA) face recognition techniques appearing within the past five years in top computer vision venues with some open issues currently overlooked by the community.
Proceedings ArticleDOI
Pose-Aware Face Recognition in the Wild
TL;DR: A method to push the frontiers of unconstrained face recognition in the wild by using multiple pose specific models and rendered face images called Pose-Aware Models (PAMs), which achieve remarkably better performance than commercial products and surprisingly also outperform methods that are specifically fine-tuned on the target dataset.
Proceedings Article
Recurrent Convolutional Strategies for Face Manipulation Detection in Videos.
TL;DR: In this article, a recurrent convolutional model was used to detect Deepfake, Face2Face and FaceSwap tampered faces in video streams, achieving state-of-the-art performance on the FaceForensics++ dataset.
Book ChapterDOI
BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization
TL;DR: B BusterNet is a pure, end-to-end trainable, deep neural network solution that outperforms state-of-the-art copy-move detection algorithms by a large margin on the two publicly available datasets, CASIA and CoMoFoD, and that is robust against various known attacks.
Proceedings ArticleDOI
Face recognition using deep multi-pose representations
Wael AbdAlmageed,Yue Wu,Stephen Rawls,Shai Harel,Tal Hassner,Iacopo Masi,Jongmoo Choi,Jatuporn Lekust,Jungyeon Kim,Prem Natarajan,Ram Nevatia,Gerard Medioni +11 more
TL;DR: A novel representation of face recognition using multiple pose-aware deep learning models achieves better results than the state-of-the-art on IARPA's CS2 and NIST's IJB-A in both verification and identification tasks.