In this paper, we present a framework of a factored deep convolutional neural network (CNN) learning for noise robust automatic speech recognition (ASR). Deep CNN architecture, which has attracted great attention in various research areas, has also been successfully applied to ASR. However, to ensure noise robustness, since merely introducing deep CNN architecture into the acoustic modeling of ...

Recognizing facial action units (AUs) from spontaneous facial expressions is still a challenging problem. Most recently, CNNs have shown promise on facial AU recognition. However, the learned CNNs are often overfitted and do not generalize well to unseen subjects due to limited AU-coded training images. We proposed a novel Incremental Boosting CNN (IB-CNN) to integrate boosting into the CNN via...

We systematically study the deep representation of random weight CNN (convolutional neural network) using the DeCNN (deconvolutional neural network) architecture. We first fix the weights of an untrained CNN, and for each layer of its feature representation, we train a corresponding DeCNN to reconstruct the input image. As compared with the pre-trained CNN, the DeCNN trained on a random weight ...

In this supplementary document, we first show how disparities relate to the 3D planes used in our representation. Next, we provide an illustration of the sampled displets for a single test image and visualize the influence of the displets with respect to the associated superpixels. For reproducibility, we also list the learned parameter settings which we used throughout all our experiments and ...

The latest High Efficiency Video Coding (HEVC) standard has been increasingly applied to generate video streams over the Internet. However, HEVC compressed videos may incur severe quality degradation, particularly at low bit-rates. Thus, it is necessary to enhance the visual quality of HEVC videos at the decoder side. To this end, this paper proposes a Quality Enhancement Convolutional Neural N...

Current research has indicated that convolution neural networks (CNNs) can work well for steganalysis in the spatial domain. There are, however, fewer works based on CNN in the JPEG domain. In this paper, we have proposed a 32layer CNN architecture that is based on Dense Convolutional Network (DenseNet) for JPEG steganalysis. The proposed CNN architecture can reuse features by concatenating fea...

BACKGROUND centrosomes are major microtubule organizing centers in animal cells, and they comprise a pair of centrioles surrounded by an amorphous pericentriolar material (PCM). Centrosome size is tightly regulated during the cell cycle, and it has recently been shown that the two centrosomes in certain stem cells are often asymmetric in size. There is compelling evidence that centrioles influe...

The Global Positioning System (GPS) is vulnerable to various deliberate and unintentional interferences. Therefore, identifying and coping with various interferences in this system is essential. This paper analyzes a method of reducing the dimensions of Cross Ambiguity Function (CAF) images in improving the identification of spoofing interference at the GPS using Multi-Layer Perceptron Neural N...

The products of the homeotic genes in Drosophila are transcription factors that are necessary to impose regional identity along the anterior-posterior axis of the developing embryo. However, the target genes under homeotic regulation that control this developmental process are largely unknown. We have utilized an immunopurification method to clone target genes of the Antennapedia protein (ANTP)...

-In this paper a parabolic equation with memory operator is considered. CNN model for such equation is made. Dynamic behavior of the CNN model is studied using describing function method. Traveling wave solutions are proved for the CNN model. An example of one-dimensional wave in medium with memory arising in classical mechanics is presented. Key-Words:Cellular Neural Networks, Partial Differen...