Convolutional neural networks (CNNs) with their ability to learn useful spatial features have revolutionized computer vision. The network topology of CNNs exploits the spatial relationship among the pixels in an image and this is one of the reasons for their success. In other domains deep learning has been less successful because it is not clear how the structure of non-spatial data can constra...

In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adve...

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D CNNs over 2D CNNs within the framework o...

The ability to recognize facial expressions automatically enables novel applications in human-computer interaction and other areas. Consequently, there has been active research in this field, with several recent works utilizing Convolutional Neural Networks (CNNs) for feature extraction and inference. These works differ significantly in terms of CNN architectures and other factors. Based on the...

Automatic classification of Human Epithelial Type-2 (HEp2) cells staining patterns is an important and yet a challenging problem. Although both shallow and deep methods have been applied, the study of deep convolutional networks (CNNs) on this topic is shallow to date, thus failed to claim its top position for this problem. In this paper, we propose a novel study of using CNNs for HEp-2 cells c...

Innovative biomedical techniques operational at the nanoscale level are being developed in therapeutics, including advanced drug delivery systems and targeted nanotherapy. Ultrathin needles provide a low invasive and highly selective means for molecular delivery and cell manipulation. This article studies the geometry and the stability of a family of packed carbon nanoneedles (CNNs) formed by u...

Kernel normalization methods have been employed to improve robustness of optimization methods to reparametrization of convolution kernels, covariate shift, and to accelerate training of Convolutional Neural Networks (CNNs). However, our understanding of theoretical properties of these methods has lagged behind their success in applications. We develop a geometric framework to elucidate underlyi...

In this paper, we propose to utilize Convolutional Neural Networks (CNNs) and the segmentation-based multi-scale analysis to locate tampered areas in digital images. First, to deal with color input sliding windows of different scales, a unified CNN architecture is designed. Then, we elaborately design the training procedures of CNNs on sampled training patches. With a set of robust multi-scale ...

In the field of computer vision, CNNs are an evolving branch of deep learning algorithms that have attracted much attention as compared to the other deep learning methods. This is because of the intrinsic property of this group of networks that explicitly construct a hierarchical representation of input images, which result in a rich set of features for downstream classification tasks. CNNs gen...

For medical students, virtual patient dialogue systems can provide useful training opportunities without the cost of employing actors to portray standardized patients. This work utilizes wordand character-based convolutional neural networks (CNNs) for question identification in a virtual patient dialogue system, outperforming a strong wordand characterbased logistic regression baseline. While t...