Search Results - "Rama Chellappa"

HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition by Ranjan, Rajeev, Patel, Vishal M., Chellappa, Rama

“…We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural…”
Get full text

Generate to Adapt: Aligning Domains Using Generative Adversarial Networks by Sankaranarayanan, Swami, Balaji, Yogesh, Castillo, Carlos D., Chellappa, Rama

“…Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the…”
Get full text

Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group by Vemulapalli, Raviteja, Arrate, Felipe, Chellappa, Rama

“…Recently introduced cost-effective depth sensors coupled with the real-time skeleton estimation algorithm of Shotton et al. [16] have generated a renewed…”
Get full text

Joint Sparse Representation and Robust Feature-Level Fusion for Multi-Cue Visual Tracking by Xiangyuan Lan, Ma, Andy J., Yuen, Pong C., Chellappa, Rama

“…Visual tracking using multiple features has been proved as a robust approach because features could complement each other. Since different types of variations…”
Get full text

Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation by Sankaranarayanan, Swami, Balaji, Yogesh, Jain, Arpit, Lim, Ser Nam, Chellappa, Rama

“…Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to…”
Get full text

Cross-View Action Recognition via Transferable Dictionary Learning by Jingjing Zheng, Zhuolin Jiang, Chellappa, Rama

“…Discriminative appearance features are effective for recognizing actions in a fixed view, but may not generalize well to a new view. In this paper, we present…”
Get full text

Predictive modeling of lean body mass, appendicular lean mass, and appendicular skeletal muscle mass using machine learning techniques: A comprehensive analysis utilizing NHANES data and the Look AHEAD study by Olshvang, Daniel, Harris, Carl, Chellappa, Rama, Santhanam, Prasanna

“…This study addresses the pressing need for improved methods to predict lean mass in adults, and in particular lean body mass (LBM), appendicular lean mass…”
Get full text

Unsupervised Domain-Specific Deblurring via Disentangled Representations by Lu, Boyu, Chen, Jun-Cheng, Chellappa, Rama

“…Image deblurring aims to restore the latent sharp images from the corresponding blurred ones. In this paper, we present an unsupervised method for…”
Get full text

Super-Resolution of Face Images Using Kernel PCA-Based Prior by Ayan Chakrabarti, Rajagopalan, A.N., Rama Chellappa

“…We present a learning-based method to super-resolve face images using a kernel principal component analysis-based prior model. A prior probability is…”
Get full text

A Learning Approach Towards Detection and Tracking of Lane Markings by Gopalan, Raghuraman, Tsai Hong, Shneier, Michael, Chellappa, Rama

“…Road scene analysis is a challenging problem that has applications in autonomous navigation of vehicles. An integral component of this system is the robust…”
Get full text

Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms by Phillips, P. Jonathon, Yates, Amy N., Hu, Ying, Hahn, Carina A., Noyes, Eilidh, Jackson, Kelsey, Cavazos, Jacqueline G., Jeckeln, Géraldine, Ranjan, Rajeev, Sankaranarayanan, Swami, Chen, Jun-Cheng, Castillo, Carlos D., Chellappa, Rama, White, David, O’Toole, Alice J.

“…Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences…”
Get full text

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction by Lin, Wei-An, Liao, Haofu, Peng, Cheng, Sun, Xiaohang, Zhang, Jingdan, Luo, Jiebo, Chellappa, Rama, Zhou, Shaohua Kevin

“…Computed tomography (CT) is an imaging modality widely used for medical diagnosis and treatment. CT images are often corrupted by undesirable artifacts when…”
Get full text

Guest Editorial: Special Issue on Deep Learning for Video Analysis and Compression by Xu, Dong, Chellappa, Rama, Van Gool, Luc, Lu, Guo

Get full text

DASH-N: Joint Hierarchical Domain Adaptation and Feature Learning by Nguyen, Hien V., Huy Tho Ho, Patel, Vishal M., Chellappa, Rama

“…Complex visual data contain discriminative structures that are difficult to be fully captured by any single feature descriptor. While recent work on domain…”
Get full text

Gaussian Conditional Random Field Network for Semantic Segmentation by Vemulapalli, Raviteja, Tuzel, Oncel, Ming-Yu Liu, Chellappa, Rama

“…In contrast to the existing approaches that use discrete Conditional Random Field (CRF) models, we propose to use a Gaussian CRF model for the task of semantic…”
Get full text

KEPLER: Simultaneous estimation of keypoints and 3D pose of unconstrained faces in a unified framework by learning efficient H-CNN regressors by Kumar, Amit, Alavi, Azadeh, Chellappa, Rama

“…Keypoint detection is one of the most important pre-processing steps in tasks such as face modeling, recognition and verification. In this paper, we present an…”
Get full text

Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation by Jie Ni, Qiang Qiu, Chellappa, Rama

“…Domain adaptation addresses the problem where data instances of a source domain have different distributions from that of a target domain, which occurs…”
Get full text

Fast object localization and pose estimation in heavy clutter for robotic bin picking by Liu, Ming-Yu, Tuzel, Oncel, Veeraraghavan, Ashok, Taguchi, Yuichi, Marks, Tim K, Chellappa, Rama

“…We present a practical vision-based robotic bin-picking system that performs detection and three-dimensional pose estimation of objects in an unstructured bin…”
Get full text

View Invariance for Human Action Recognition by Parameswaran, Vasu, Chellappa, Rama

“…This paper presents an approach for viewpoint invariant human action recognition, an area that has received scant attention so far, relative to the overall…”
Get full text

Towards transforming malaria vector surveillance using VectorBrain: a novel convolutional neural network for mosquito species, sex, and abdomen status identifications by Li, Deming, Hegde, Shruti, Sunil Kumar, Aravind, Zacharias, Atul, Mehta, Parthvi, Mukthineni, Venkat, Srimath, Satwik, Patel, Sunny, Suin, Maitreya, Chellappa, Rama, Acharya, Soumyadipta

“…Malaria is a major public health concern, causing significant morbidity and mortality globally. Monitoring the local population density and diversity of the…”
Get full text