T
Tianyue Zheng
Researcher at Beijing University of Posts and Telecommunications
Publications - 13
Citations - 329
Tianyue Zheng is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 3, co-authored 4 publications receiving 190 citations.
Papers
More filters
Posted Content
Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
TL;DR: A Cross-Age LFW is constructed which deliberately searches and selects 3,000 positive face pairs with age gaps to add aging process intra-class variance and evaluate several metric learning and deep learning methods on the new database.
Proceedings ArticleDOI
Age Estimation Guided Convolutional Neural Network for Age-Invariant Face Recognition
TL;DR: This work proposes a novel deep face recognition network called age estimation guided convolutional neural network (AE-CNN) to separate the variations caused by aging from the personspecific features which are stable.
Proceedings ArticleDOI
CORE-lens: simultaneous communication and object recognition with disentangled-GAN cameras
Ziwei Liu,Tianyue Zheng,Chao Hu,Yanbing Yang,Yimao Sun,Yi Zhang,Zhe Chen,Liangyin Chen,Jun Luo +8 more
TL;DR: CORE-Lens exploits the idea of disentangled representation learning to separate the mixed signals in the feature space: while the GAN-reconstructed clean background images are used to perform object recognition, OCC decoding is conducted on the residual of the original image after subtracting the reconstructed background.
Journal ArticleDOI
Catch Your Breath: Simultaneous RF Tracking and Respiration Monitoring with Radar Pairs
TL;DR: Zhang et al. as discussed by the authors designed an encoder-decoder deep neural network driven by variational inference to recover fine-grained respiratory waveforms from complex RF reflection mixtures.
Proceedings ArticleDOI
Deep probabilities for age estimation
TL;DR: The proposed method: Deep Probabilities (DP) of facial age shows improvements over direct regression and multi-classification methods.