This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario.
If a CNN is intended to tolerate facial pose, then we face an important question: should this training data be diverse in its pose distribution, or should face images be normalized to a single pose in a pre-processing step?
On the other hand, KD is proved to be useful for model compression for the FER problem, and we discovered that its effects gets more and more significant with the decreasing model size.
In this paper, we propose an approach to representing high-order information for temporal action segmentation via a simple yet effective bilinear form.
In this paper, we propose to tackle these three challenges in an new alignment framework termed 3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks.
SOTA for Face Alignment on AFLW
In this study, we present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images.
However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces.
SOTA for Face Identification on IJB-A
SCENE text recognition has attracted great interest from the academia and the industry in recent years owing to its importance in a wide range of applications.