R
Ran He
Researcher at Chinese Academy of Sciences
Publications - 330
Citations - 11787
Ran He is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Facial recognition system & Computer science. The author has an hindex of 47, co-authored 303 publications receiving 8707 citations. Previous affiliations of Ran He include Dalian University of Technology & Nanyang Technological University.
Papers
More filters
Proceedings Article
Adversarial Discriminative Heterogeneous Face Recognition.
TL;DR: In this paper, an adversarial discriminative feature learning framework is proposed to close the sensing gap via adversarial learning on both raw-pixel space and compact feature space, which integrates cross-spectral face hallucination and discriminive feature learning into an end-to-end adversarial network.
Proceedings Article
Coupled Deep Learning for Heterogeneous Face Recognition.
TL;DR: Wang et al. as mentioned in this paper proposed a coupled deep learning (CDL) approach for heterogeneous face matching, which seeks a shared feature space in which the heterogenous face matching problem can be approximately treated as a homogeneous face mapping problem.
Journal ArticleDOI
Disentangled Variational Representation for Heterogeneous Face Recognition
TL;DR: In this paper, a disentangled variational representation (DVR) was proposed for cross-modal matching, where a variational lower bound was employed to optimize the approximate posterior for NIR and VIS representations.
Journal Article
Everybody's Talkin': Let Me Talk as You Want
TL;DR: A method to edit a target portrait footage by taking a sequence of audio as input to synthesize a photo-realistic video, which is end-to-end learnable and robust to voice variations in the source audio.
Proceedings ArticleDOI
Make a Face: Towards Arbitrary High Fidelity Face Manipulation
TL;DR: This work proposes Additive Focal Variational Auto-encoder (AF-VAE), a novel approach that can arbitrarily manipulate high-resolution face images using a simple yet effective model and only weak supervision of reconstruction and KL divergence losses.