Ran He

TL;DR: In this paper, an introspective variational autoencoder (IntroVAE) model is proposed to synthesize high-resolution photographic images, which is capable of self-evaluating the quality of its generated samples and improving itself accordingly.

TL;DR: This paper models high-resolution heterogeneous face synthesis as a complementary combination of two components: a texture inpainting component and a pose correction component and demonstrates that by attaching the correction component, it can simplify heterogenous face synthesis from one-to-many unpaired image translation to one- to-one paired image translation, and minimize the spectral and pose discrepancy during heterogeneous recognition.

TL;DR: A single near infrared (NIR) image is used as the input, and a mapping from the NIR Tensor space to 3D tensor space, learned by using statistical learning, is used for the shape recovery.

TL;DR: A novel approach called Source HypOthesis Transfer (SHOT), which learns the feature extraction module for the target domain by fitting the target data features to the frozen source classification module (representing classification hypothesis), and which exploits both information maximization and self-supervised learning for the feature extractor learning.

TL;DR: A comprehensive survey of recent audio-visual learning development can be found in this article, where the authors divide the current audio visual learning tasks into four different subfields: audio visual separation and localization, audio visual correspondence learning, audiovisual generation, and audio visual representation learning.