18 citations · 22 across the 4 of their papers we have counts for
5 papers · 1 filter
Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation
Jiaxin Gu, Ce Li, Baochang Zhang +4
The advancement of deep convolutional neural networks (DCNNs) has driven significant improvement in the accuracy of recognition systems for many computer vision tasks. However, the…
Memory Attention Networks for Skeleton-based Action Recognition
Chunyu Xie, Ce Li, Baochang Zhang +4
Skeleton-based action recognition task is entangled with complex spatio-temporal variations of skeleton joints, and remains challenging for Recurrent Neural Networks (RNNs). In thi…
Deep Fisher Discriminant Learning for Mobile Hand Gesture Recognition
Chunyu Xie, Ce Li, Baochang Zhang +2
Gesture recognition is a challenging problem in the field of biometrics. In this paper, we integrate Fisher criterion into Bidirectional Long-Short Term Memory (BLSTM) network and…
GM-Net: Learning Features with More Efficiency
Yujia Chen, Ce Li
Deep Convolutional Neural Networks (CNNs) are capable of learning unprecedentedly effective features from images. Some researchers have struggled to enhance the parameters' efficie…
Deep Spatio-temporal Manifold Network for Action Recognition
Ce Li, Chen Chen, Baochang Zhang +3
Visual data such as videos are often sampled from complex manifold. We propose leveraging the manifold structure to constrain the deep action feature learning, thereby minimizing t…