G Cheng, P Zhou, J Han - Proceedings of the IEEE conference on …, 2016 - cv-foundation.org
Thanks to the powerful feature representations obtained through deep convolutional neural network (CNN), the performance of object detection has recently been substantially boosted …
Two popular representation learning paradigms are dictionary learning and deep learning. While dictionary learning focuses on learning “basis” and “features” by matrix factorization …
L Zhang, D Zhang - IEEE transactions on neural networks and …, 2016 - ieeexplore.ieee.org
Conventional extreme learning machines (ELMs) solve a Moore–Penrose generalized inverse of hidden layer activated matrix and analytically determine the output weights to …
Recently, a multi-view dictionary learning (DL) technique has received much attention. Although some multi-view DL methods have been presented, they suffer from the problem of …
Deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which are …
Z Zhang, F Li, M Zhao, L Zhang… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
Recovering low-rank and sparse subspaces jointly for enhanced robust representation and classification is discussed. Technically, we first propose a transductive low-rank and sparse …
W Liu, ZJ Zha, Y Wang, K Lu… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many …
T Zhang, W Jia, X He, J Yang - IEEE transactions on circuits …, 2016 - ieeexplore.ieee.org
Automatic violence detection from video is a hot topic for many video surveillance applications. However, there has been little success in developing an algorithm that can …
Q Liu, C Liu - IEEE transactions on neural networks and …, 2016 - ieeexplore.ieee.org
A locally linear K Nearest Neighbor (LLK) method is presented in this paper with applications to robust visual recognition. Specifically, the concept of an ideal representation …