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 ArticleDOI
Cross-Spectral Face Hallucination via Disentangling Independent Factors
TL;DR: Zhang et al. as mentioned in this paper proposed a Pose Aligned Cross-spectral Hallucination (PACH) approach to disentangle the independent factors and deal with them in individual stages.
Proceedings ArticleDOI
Pose-preserving Cross Spectral Face Hallucination
TL;DR: This work presents an approach to avert the data misalignment problem and faithfully preserve pose, expression and identity information during cross-spectral face hallucination and outperforms current state-of-the-art HFR methods at a high resolution.
Posted Content
Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification
TL;DR: Li et al. as discussed by the authors proposed a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN) to alleviate the negative effects from makeup, and then used the synthesized non-makeup images for further verification.
Book ChapterDOI
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
TL;DR: In this article, the authors proposed a balanced adversarial alignment (BAA) and adaptive uncertainty suppression (AUS) to solve the problem of negative transfer and uncertainty propagation in unsupervised domain adaptation.
Book ChapterDOI
TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search
TL;DR: This paper rethink three freedoms of differentiable NAS, i.e. operation-level, depth-level and width- level, and proposes a novel method, named Three-Freedom NAS (TF-NAS), to achieve both good classification accuracy and precise latency constraint.