• Publications
  • Influence
Image Formation Process
CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection
A face detection approach named Contextual Multi-Scale Region-based Convolution Neural Network (CMS-RCNN) to robustly solve the problems mentioned above and allows explicit body contextual reasoning in the network inspired from the intuition of human vision system. Expand
Feature Selective Anchor-Free Module for Single-Shot Object Detection
The FSAF module robustly improves the baseline RetinaNet by a large margin under various settings, while introducing nearly free inference overhead, and the resulting best model can achieve a state-of-the-art 44.6% mAP, outperforming all existing single-shot detectors on COCO. Expand
Local Binary Convolutional Neural Networks
Empirically, CNNs with LBC layers, called local binary convolutional neural networks (LBCNN), achieves performance parity with regular CNNs on a range of visual datasets while enjoying significant computational savings. Expand
Bounding Box Regression With Uncertainty for Accurate Object Detection
A novel bounding box regression loss that greatly improves the localization accuracies of various architectures with nearly no additional computation and allows us to merge neighboring bounding boxes during non-maximum suppression (NMS), which further improves the globalization performance. Expand
Correlation Pattern Recognition for Face Recognition
A new method is discussed called the class-dependence feature analysis (CFA) that reduces the computational complexity of correlation pattern recognition and the results of applying CFA to the FRGC phase-II data are shown. Expand
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions
This paper proposes to generalize the traditional Sign and PReLU functions to enable explicit learning of the distribution reshape and shift at near-zero extra cost and shows that the proposed ReActNet outperforms all the state-of-the-arts by a large margin. Expand
Unconstrained Pose-Invariant Face Recognition Using 3D Generic Elastic Models
This paper proposes a new method for real-world unconstrained pose-invariant face recognition using the 3D Generic Elastic Model (3D GEM) approach and presents convincing results on challenging data sets and video sequences demonstrating high recognition accuracy under controlled as well as unseen, uncontrolled real- world scenarios using a fast implementation. Expand
NIR-VIS heterogeneous face recognition via cross-spectral joint dictionary learning and reconstruction
This paper develops a method to reconstruct VIS images in the NIR domain and vice-versa using a cross-spectral joint ℓ0 minimization based dictionary learning approach to learn a mapping function between the two domains. Expand
Ring Loss: Convex Feature Normalization for Face Recognition
This work motivates and presents Ring loss, a simple and elegant feature normalization approach for deep networks designed to augment standard loss functions such as Softmax, and applies soft normalization, where it gradually learns to constrain the norm to the scaled unit circle while preserving convexity leading to more robust features. Expand