… on occluded faces. In order to determine the importance of different facial parts, the face
detection … the CFP dataset and remove different areas of each face: We overlay a grid over each …

… (1) Generating face parts responses from attribute-aware deep networks: We believe the …
structure of local facial parts (eg eyes, nose, mouths) is the key to address face detection in …

… network (CNN) for face detection leveraging on facial attributes based supervision. We
observe a phenomenon that part … uncropped face images, without any explicit part supervision. …

… of face detection and we propose a light-weight deep convolutional neural network that …
training and run time and outperforms the convolutional network used in [1] for the same task…

… uncropped face images, without any explicit part supervision. … for finding faces through
scoring facial parts responses by … networks to generate response maps of different facial parts. …

… other in the weight of feature map concatenation. A variety of strategies is introduced in our
face detection network, … [18] exploited facial landmarks as supervision signals to improve face …

… popular face detection benchmark datasets show that our single-model face detector algorithm
… are more complex and require annotations of either different poses or facial landmarks. …

… Face detection is a critical step to all facial analysis algorithms, including … convolutional
networks. We anticipate that the new WIDER FACE data can benefit deep convolutional network …

… different poses, scales, illumination, occlusion, etc, face … (facial part) vary from one face to
another. Current detectors, however, particularly those based on convolutional neural networks…

… real-time face detection. Specifically, we adopt the convolutional neural network cascade as
… the dense image pyramid has to go through the network. To address this issue, we reduce …