A5101768429- Face recognition and analysis
- Face and Expression Recognition
- Biometric Identification and Security
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Human Pose and Action Recognition
- Anomaly Detection Techniques and Applications
- Generative Adversarial Networks and Image Synthesis
- Time Series Analysis and Forecasting
- Advanced Vision and Imaging
- Gaze Tracking and Assistive Technology
- Retinal and Optic Conditions
- Multimodal Machine Learning Applications
- Data Stream Mining Techniques
- Advanced Neural Network Applications
- Retinal Imaging and Analysis
- Advanced Optimization Algorithms Research
- Medical Image Segmentation Techniques
- User Authentication and Security Systems
- Face Recognition and Perception
- Speech and Audio Processing
- Human Mobility and Location-Based Analysis
- Image and Object Detection Techniques
- Video Analysis and Summarization
- Advanced Image Processing Techniques
Amazon (United States)
2020-2021
Seattle University
2021
University of Maryland, College Park
2015-2020
Galgotias University
2019
Research Institute for Advanced Computer Science
2019
Park University
2016
Indian Institute of Technology Kharagpur
2011
We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a CNN separate followed by multi-task learning that operates on fused features. It exploits synergy among tasks which boosts up their individual performances. Additionally, we propose two variants HyperFace: (1) HyperFace-ResNet builds ResNet-101 model...
We present a multi-purpose algorithm for simultaneous face detection, alignment, pose estimation, gender recognition, smile age estimation and recognition using single deep convolutional neural network (CNN). Theproposed method employs multi-task learning framework that regularizes the shared parameters of CNN builds synergy among different domains tasks. Extensive experiments show has better understanding achieves state-of-the-art result most these
Significance This study measures face identification accuracy for an international group of professional forensic facial examiners working under circumstances that apply in real world casework. Examiners and other human “specialists,” including forensically trained reviewers untrained superrecognizers, were more accurate than the control groups on a challenging test identification. Therefore, specialists are best available solution to problem We present data comparing state-of-the-art...
Recent progress in face detection (including keypoint detection), and recognition is mainly being driven by (i) deeper convolutional neural network architectures, (ii) larger datasets. However, most of the large datasets are maintained private companies not publicly available. The academic computer vision community needs more varied to make further progress. In this paper, we introduce a new dataset, called UMDFaces, which has 367,888 annotated faces 8,277 subjects. We also evaluation...
Recent developments in deep convolutional neural networks (DCNNs) have shown impressive performance improvements on various object detection/recognition problems. This has been made possible due to the availability of large annotated data and a better understanding nonlinear mapping between images class labels, as well affordability powerful graphics processing units (GPUs). These learning also improved capabilities machines faces automatically executing tasks face detection, pose...
The availability of large annotated datasets and affordable computation power have led to impressive improvements in the performance convolutional neural networks (CNNs) on various face analysis tasks. In this paper, we describe a deep learning pipeline for unconstrained identification verification which achieves state-of-the-art several benchmark datasets. We provide design details modules involved automatic recognition: detection, landmark localization alignment,...
We present a face detection algorithm based on Deformable Part Models and deep pyramidal features. The proposed method called DP2MFD is able to detect faces of various sizes poses in unconstrained conditions. It reduces the gap training testing DPM features by adding normalization layer convolutional neural network (CNN). Extensive experiments four publicly available datasets show that our capture meaningful structure performs significantly better than many competitive algorithms.
In this paper, we present an end-to-end system for the unconstrained face verification problem based on deep convolutional neural networks (DCNN). The consists of three modules detection, alignment and is evaluated using newly released IARPA Janus Benchmark A (IJB-A) dataset its extended version Challenging set 2 (JANUS CS2) dataset. IJB-A CS2 datasets include real-world faces 500 subjects with significant pose illumination variations which are much harder than Labeled Faces in Wild (LFW)...
While the research community appears to have developed a consensus on methods of acquiring annotated data, design and training CNNs, many questions still remain be answered. In this paper, we explore following that are critical face recognition research: (i) Can train images expect systems work videos? (ii) Are deeper datasets better than wider datasets? (iii) Does adding label noise lead improvement in performance deep networks? (iv) Is alignment needed for recognition? We address these by...
We propose a coarse-to-fine approach for estimating the apparent age from unconstrained face images using deep convolutional neural networks (DCNNs). The proposed method consists of three modules. first one is DCNN-based group classifier which classifies given image into groups. second module collection regressors compute fine-grained estimate corresponding in each class. Finally, any erroneous prediction corrected an error-correcting mechanism. Experimental evaluations on publicly available...
Unconstrained remote gaze tracking using off-the-shelf cameras is a challenging problem. Recently, promising algorithms for appearance-based estimation convolutional neural networks (CNN) have been proposed. Improving their robustness to various confounding factors including variable head pose, subject identity, illumination and image quality remain open problems. In this work, we study the effect of pose on machine learning regressors trained estimate direction. We propose novel branched...
Although deep learning approaches have achieved performance surpassing humans for still image-based face recognition, unconstrained video-based recognition is a challenging task due to large volume of data be processed and intra/inter-video variations on pose, illumination, occlusion, scene, blur, video quality, etc. In this work, we consider scenarios from multiple-shot videos surveillance with low-quality frames. To handle these problems, propose robust efficient system which composed...
We propose an approach for age estimation from unconstrained images based on deep convolutional neural networks (DCNN). Our method consists of four steps: face detection, alignment, DCNN-based feature extraction and network regression estimation. The proposed exploits two insights: (1) Features obtained DCNN trained face-identification task can be used (2) three-layer Gaussian loss performs better than traditional methods apparent is evaluated the challenge developed ICCV 2015 ChaLearn...
Unconstrained face verification is a challenging problem owing to variations in pose, illumination, resolution of image, age, etc. This becomes even more complex when the subjects are actively trying deceive systems by wearing disguise. The under consideration here identify subject disguises and reject impostors look like interest. In this paper we present DCNN-based approach for recognizing people picking out impostors. We train two different networks on large dataset comprising still...
Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of actions. In this paper, we present a modular system untrimmed surveillance videos. We propose two stage approach. The first generates dense proposals using hierarchical clustering jittering techniques on frame-wise object detections. second is Temporal Refinement I3D (TRI-3D) network that performs classification refinement generated proposals. detection-based proposal...
We present an algorithm for extracting key-point descriptors using deep convolutional neural networks (CNN). Unlike many existing CNNs, our model computes local features around a given point in image. also face alignment based on regression these descriptors. The proposed method called Local Deep Descriptor Regression (LDDR) is able to localize landmarks of varying sizes, poses and occlusions with high accuracy. Descriptors presented this paper are uniquely efficiently describe every pixel...
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 videos as inputs and output the labels of objects input data. Computer vision methods use representations derived based on geometric, radiometric neural considerations statistical structural matchers artificial network-based where a multi-layer network learns mapping from to class provided competing approaches problems. last four years, Deep...