The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Recently, deep learning has enjoyed a great deal of success for computer vision problems due to its capability to model highly complex tasks, such as image classification, object detection, face recognition, among many others. Although these neural networks are nowadays very powerful, there is a huge amount of parameters (i.e. the model) that need to be learned and require considerable storage space...
The present paper has considered multithreshold decoders for self-orthogonal codes providing a near-optimal efficiency of the error correction under linear computational complexity. New divergence principle used within construction and decoding convolutional codes has been discussed. The paper has shown that usage of such principle allows significantly approximating an area of the decoder effective...
Convolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision. In contrast to recent supervised methods, CSC allows for convolutional image representations to be learned that are equally useful for high-level vision tasks and low-level image reconstruction and can be applied to a wide range of tasks without problem-specific retraining. Due to their extreme...
Convolutional sparse coding (CSC) plays an essential role in many computer vision applications ranging from image compression to deep learning. In this work, we spot the light on a new application where CSC can effectively serve, namely line drawing analysis. The process of drawing a line drawing can be approximated as the sparse spatial localization of a number of typical basic strokes, which in...
The success of fine-grained visual categorization (FGVC) extremely relies on the modeling of appearance and interactions of various semantic parts. This makes FGVC very challenging because: (i) part annotation and detection require expert guidance and are very expensive; (ii) parts are of different sizes; and (iii) the part interactions are complex and of higher-order. To address these issues, we...
NarrowBand Waveforms (NBWF) are often used in VHF or UHF tactical communications. For these kinds of waveforms, low latency and robust data rates result in short codeword lengths that are challenging in terms of channel coding. Usually, serially concatenated convolutional code and continuous phase modulation (CC-CPM) schemes are considered in the context of NBWF. When evaluating the achievable rates,...
A new type of channel in order to analyze burst noise is introduced. As opposed to the well known Gilbert-Elliott Markov and Polya contagion channels previously analyzed in the literature, burst run one's lengths based on the logarithmic distribution are introduced. The main property of this new model is that the conditional probability of having an erroneous bit given a previous run one's length...
Developing a technique for the automatic analysis of surveillance videos in order to identify the presence of violence is of broad interest. In this work, we propose a deep neural network for the purpose of recognizing violent videos. A convolutional neural network is used to extract frame level features from a video. The frame level features are then aggregated using a variant of the long short term...
In this paper, we propose a chaotic convolutional encryption scheme based on multiple chaos mapping. The scheme employs the characteristics of pseudo randomness and sensitivity to initial conditions of chaos mapping. It generates time-varying state transition matrix through modulo-two adder between multiple chaos sequences and input data as well as the state values of status registers in convolutional...
Distributed storage systems are composed by many unreliable storage nodes over a network. A data file is redundantly stored in multiple storage nodes to provide high reliability. Recently erasure codes with Maximum Distance Separable (MDS) property are gradually employed in distributed storage systems to reduce the cost of reliably storing large amounts of data. Regenerating codes are a class of erasure...
We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from distinct components, using standard encoders with separate off-the-shelf features such as SIFT descriptors or pre-trained CNN features for material recognition. Our...
In this paper, we revisit the LASSO sparse representation problem, which has been studied and used in a variety of different areas, ranging from signal processing and information theory to computer vision and machine learning. In the vision community, it found its way into many important applications, including face recognition, tracking, super resolution, image denoising, to name a few. Despite advances...
Face recognition has been an important task in pattern recognition and computer vision. Recently, sparse representation has become a popular data representation method in face recognition field. Convolutional sparse coding, which replaces the linear combination of a set of dictionary atoms with the sum of s series of mapping term convoluted with the dictionary filters, was proposed to improve the...
Several recent works interpret convolutional features produced by deep convolutional neural networks as local descriptors. Existing high-dimensional aggregation based methods, e.g., Fisher Vector (FV) obtain inferior performance to pooling based methods in most situations, and we observe that it is mainly caused by the ignorance of spatial weights. In this paper, we propose a novel method named spatial...
Nowadays small satellites are promising tools for space research and communication. However, size restrictions are also limits for power consumption and capacity. One of the ways to improve the throughput is the use appropriate modulation and coding schemes. A suitable channel model was chosen and link budgets were calculated for the appropriate choice of modulation and coding. Different types of...
This paper proposes a novel deep convolutional neural network (CNN), called sparse coding convolutional neural network (SC-CNN), to address the problem of sound event recognition and retrieval task. Unlike the general framework of a CNN, in which feature learning process is performed hierarchically, the proposed framework models the whole memorizing procedures in the human brain, including encoding,...
The decoding problem is addressed in this paper for the scenario that convolutional codes are employed at the source node of the network with linear or convolutional network coding for error correction. Since network errors may disperse or neutralize due to network coding, decoding cannot be done at sink nodes merely based on the minimum Hamming distance between the received and sent sequence. Source...
Extensive studies have demonstrated the effectiveness of constructing capacity-approaching codes by block Markov superposition transmission (BMST). However, to achieve high performance, BMST codes typically require large encoding memories and large decoding window sizes, which result in increased decoding complexity and decoding latency. To address this issue, we introduce the recursive BMST (rBMST),...
Hierarchical approaches for representation learning have the ability to encode relevant features at multiple scales or levels of abstraction. However, most hierarchical approaches exploit only the last level in the hierarchy, or provide a multiscale representation that holds a significant amount of redundancy. We argue that removing redundancy across the multiple levels of abstraction is important...
Channel coding is a fundamental building block in any communications system. High performance codes, with low complexity encoding and decoding are a must-have for future wireless systems, with requirements ranging from the operation in highly reliable scenarios, utilizing short information messages and low code rates, to high throughput scenarios, working with long messages, and high code rates. We...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.