We have presented Selective Refinement Network, a novel single shot face detector, which consists of two key modules, i.e., the step Classification and the step Regression
The Faster R-convolutional neural networks is designed for generic object detection, it demonstrates impressive face detection performance when retrained on a suitable face detection training set
We propose a two-stream network for face tampering detection. We train GoogLeNet to detect tampering artifacts in a face classification stream, and train a patch based triplet network to leverage features capturing local noise residuals and camera characteristics as a second stre...
The popularity of convolutional neural network in computer vision domain largely comes from its translation invariance property, which significantly reduces computation and model size compared to fully-connected neural networks
Experimental results demonstrate that our methods consistently outperform the state-of-the-art methods across several challenging benchmarks while keeping real time performance
By combining the center loss with the softmax loss to jointly supervise the learning of Convolutional neural networks, the discriminative power of the deeply learned features can be highly enhanced for robust face recognition
We provide concrete measurement set for people to evaluate the model performance and provide, to the best of our knowledge, the largest training dataset to facilitate research in the area
We wish to encourage the community to focusing on some inherent challenges of face detection – small scale, occlusion, and extreme poses. These factors are ubiquitous in many real world applications