R
Rama Chellappa
Researcher at Johns Hopkins University
Publications - 1062
Citations - 70523
Rama Chellappa is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Facial recognition system & Motion estimation. The author has an hindex of 120, co-authored 1031 publications receiving 62865 citations. Previous affiliations of Rama Chellappa include Mitsubishi Electric Research Laboratories & Indian Institute of Technology, Jodhpur.
Papers
More filters
Journal ArticleDOI
Face recognition: A literature survey
TL;DR: In this paper, the authors provide an up-to-date critical survey of still-and video-based face recognition research, and provide some insights into the studies of machine recognition of faces.
Proceedings ArticleDOI
Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group
TL;DR: A new skeletal representation that explicitly models the 3D geometric relationships between various body parts using rotations and translations in 3D space is proposed and outperforms various state-of-the-art skeleton-based human action recognition approaches.
Journal ArticleDOI
Machine Recognition of Human Activities: A Survey
TL;DR: A comprehensive survey of efforts in the past couple of decades to address the problems of representation, recognition, and learning of human activities from video and related applications is presented.
Proceedings ArticleDOI
Soft-NMS — Improving Object Detection with One Line of Code
TL;DR: Soft-NMS as mentioned in this paper decays the detection scores of all other objects as a continuous function of their overlap with M. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss.
Journal ArticleDOI
HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition
TL;DR: HyperFace as discussed by the authors combines face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNNs) and achieves significant improvement in performance by fusing intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features.