Face detection is the task of detecting faces in a photo or video (and distinguishing them from other objects).
( Image credit: FaceBoxes )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
For human it is very easy to recognize those emotions but for computer it is very challenging.
In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors.
We consider universal adversarial patches for faces - small visual elements whose addition to a face image reliably destroys the performance of face detectors.
Furthermore, based on YOLOv2, we design IFQ-Tinier-YOLO face detector which is a fixed-point network with 256x reduction in model size (246k Bytes) than Tiny-YOLO.
Advances in computer vision have brought us to the point where we have the ability to synthesise realistic fake content.
Firstly, we employ weights with duplicated channels for the weight-intensive layers to reduce the model size.
We use a Generative Adversarial Network for the task of retrieving the garment that the person in the image was wearing.
Benefiting from the advance of deep convolutional neural network approaches (CNNs), many face detection algorithms have achieved state-of-the-art performance in terms of accuracy and very high speed in unconstrained applications.
In this paper, we perform a comparative performance analysis of some of the well known face detection methods including the few used in that competition, and, compare them to our proposed body pose based face detection method.