← Search

Pengju Yang

2 accepted papers

2022

Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression

CVPR 2022poster

Learning from a label distribution has achieved promising results on ordinal regression tasks such as facial age and head pose estimation wherein, the concept of adaptive label distribution learning (ALDL) has drawn lots of attention recently for its superiority in theory. However, compared with the…

Cited by 29PDFScholar
2021

Demodalizing Face Recognition with Synthetic Samples

AAAI 2021technical

Using data generated by generative adversarial networks or three-dimensional (3D) technology for face recognition training is a theoretically reasonable solution to the problems of unbalanced data distributions and data scarcity. However, due to the modal difference between synthetic data and real d…