Deep convolutional network cascade for facial point detection
We propose a new approach for estimation of the positions of facial keypoints with three-level
carefully designed convolutional networks. At each level, the outputs of multiple networks …
carefully designed convolutional networks. At each level, the outputs of multiple networks …
Deep learning face representation from predicting 10,000 classes
This paper proposes to learn a set of high-level feature representations through deep learning,
referred to as Deep hidden IDentity features (DeepID), for face verification. We argue that …
referred to as Deep hidden IDentity features (DeepID), for face verification. We argue that …
Clinical features and outcomes of pregnant women suspected of coronavirus disease 2019
G Sun, F Tang, M Peng, Y Gao, J Peng, H Xie, Y Zhao… - Journal of infection, 2020 - Elsevier
… Author links open overlay panel yang Hui a 1 , Sun Guoqiang a 1 , Tang Fei a , Peng Min a ,
Gao Ying a , Peng … Tang Fei: Investigation. Peng Min: Investigation. Gao Ying: Investigation. …
Gao Ying a , Peng … Tang Fei: Investigation. Peng Min: Investigation. Gao Ying: Investigation. …
Deeply learned face representations are sparse, selective, and robust
This paper designs a high-performance deep convolutional network (DeepID2+) for face
recognition. It is learned with the identification-verification supervisory signal. By increasing the …
recognition. It is learned with the identification-verification supervisory signal. By increasing the …
Triphenylamine-based π-conjugated dendrimers: Convenient synthesis, easy solution processability, and good hole-transporting properties
Z Li, T Ye, S Tang, C Wang, D Ma, Z Li - Journal of Materials Chemistry …, 2015 - pubs.rsc.org
Two, third-generation triphenylamine-based dendrimers (DT1 and DT2) were prepared
through a simple convergent approach by using a combination of versatile carbon–carbon …
through a simple convergent approach by using a combination of versatile carbon–carbon …
Stimulus-responsive shape memory materials: A review
…, Z Ding, Y Zhao, CC Wang, H Purnawali, C Tang - Materials & Design, 2012 - Elsevier
Stimulus-responsive materials are able to response to a particular stimulus, such as, heat,
chemical, and light. As such, they are smarter and more intelligent than ordinary materials. …
chemical, and light. As such, they are smarter and more intelligent than ordinary materials. …
Emerging pollutants in water environment: Occurrence, monitoring, fate, and risk assessment
Y Tang, M Yin, W Yang, H Li, Y Zhong… - Water Environment …, 2019 - Wiley Online Library
The occurrence of emerging pollutants (EPs) is continuously reported worldwide. Nevertheless,
only few of these compounds are toxicologically evaluated due to their vast numbers. …
only few of these compounds are toxicologically evaluated due to their vast numbers. …
A decade's studies on metastasis of hepatocellular carcinoma
ZY Tang, SL Ye, YK Liu, LX Qin, HC Sun, QH Ye… - Journal of cancer …, 2004 - Springer
Metastasis remains one of the major challenges before hepatocellular carcinoma (HCC) is
finally conquered. This paper summarized a decade’s studies on HCC metastasis at the Liver …
finally conquered. This paper summarized a decade’s studies on HCC metastasis at the Liver …
Hybrid deep learning for face verification
This paper proposes a hybrid convolutional network (ConvNet)-Restricted Boltzmann Machine
(RBM) model for face verification in wild conditions. A key contribution of this work is to …
(RBM) model for face verification in wild conditions. A key contribution of this work is to …
Deep learning face representation by joint identification-verification
The key challenge of face recognition is to develop effective feature representations for
reducing intra-personal variations while enlarging inter-personal differences. In this paper, we …
reducing intra-personal variations while enlarging inter-personal differences. In this paper, we …