activity
20152023
most citedL2-constrained Softmax Loss for Discriminative Face Verification

277 citations · 473 across the 13 of their papers we have counts for

collaborators
Showing 2016Show all

6 papers · 1 filter

cs.CV2016★ 22 cited

An All-In-One Convolutional Neural Network for Face Analysis

Rajeev Ranjan, Swami Sankaranarayanan, Carlos D. Castillo +1

We present a multi-purpose algorithm for simultaneous face detection, face alignment, pose estimation, gender recognition, smile detection, age estimation and face recognition usin…

cs.CV2016

UMDFaces: An Annotated Face Dataset for Training Deep Networks

Ankan Bansal, Anirudh Nanduri, Carlos Castillo +2

Recent progress in face detection (including keypoint detection), and recognition is mainly being driven by (i) deeper convolutional neural network architectures, and (ii) larger d…

cs.CV2016

Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks

Jun-Cheng Chen, Rajeev Ranjan, Swami Sankaranarayanan +5

Over the last five years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems.…

cs.CV2016

HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

Rajeev Ranjan, Vishal M. Patel, Rama Chellappa

We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed…

cs.CV2016★ 20 cited

Face Alignment by Local Deep Descriptor Regression

Amit Kumar, Rajeev Ranjan, Vishal Patel +1

We present an algorithm for extracting key-point descriptors using deep convolutional neural networks (CNN). Unlike many existing deep CNNs, our model computes local features aroun…

cs.CV2016

Towards the Design of an End-to-End Automated System for Image and Video-based Recognition

Rama Chellappa, Jun-Cheng Chen, Rajeev Ranjan +4

Over many decades, researchers working in object recognition have longed for an end-to-end automated system that will simply accept 2D or 3D image or videos as inputs and output th…