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.
Visual matching algorithms can be described in terms of visual content representation and similarity measure. With local feature based representations, visual matching can be restated as: 1) how to obtain visual similarity from the local kernel matrix, and 2) how to calculate the local kernel matrix effectively and efficiently. Existing methods mostly focus on the former, and use Euclidean distance...
We present algorithms for initializing networks that use a convolutional network coding scheme and that may contain cycles. During the initialization process every source node transmits basis vectors and every sink node measures the impulse response of the network. The impulse response is then used to find a relation between the transmitted and the received symbols, which is needed for a decoding...
A collection of files can be compressed by storing each file in the collection as a delta file: one file refers to several other files. The copy instructions in a delta file could reference other files either in their encoded forms or in their (original) unencoded forms. Because files are stored compressed, the latter approach suffers from a blowout in the number of files that need to be decoded to...
Certain problems encountered in electrical engineering incur an exponential time complexity and are therefore impossible to solve exactly for all problem sizes. However, heuristical approaches can sometimes use exact solutions of small instances of a problem to formulate a suboptimal solution to a larger instance of the problem. This paper demonstrates how to use the Unrank algorithm to solve small...
The analysis of human brain connectivity networks has become an increasingly prevalent task in neuroimaging. A few recent studies have shown the possibility of decoding brain states based on brain graph classification. Graph kernels have emerged as a powerful tool for graph comparison that allows the direct use of machine learning classifiers on brain graph collections. They allow classifying graphs...
In this paper we present the Synaptic Kernel Adaptation Network (SKAN) circuit, a dynamic circuit that implements Spike Timing Dependent Plasticity (STDP), not by adjusting synaptic weights but via dynamic synaptic kernels. SKAN performs unsupervised learning of the commonest spatio-temporal pattern of input spikes using simple analog or digital circuits. It features tunable robustness to temporal...
A new sparse graph-embedded dimensionality reduction (DR) method for hyperspectral image classification is proposed in this paper. The proposed method incorporates the contextual information and the class information to address the supervised transform-based DR problems. On one hand, a class-oriented sparse graph construction method is proposed, where the contextual information is integrated via a...
Solving a multiple-valued problem means to assign values to a given set of multiple-valued variables such that certain conditions are satisfied. The solution of a multiplevalued problem is a subset of vk v-valued tuples of the length k, where k is the number of variables and v is the number of their possible values. This paper compares several approaches which solve such problems. These approaches...
This paper proposes a new system for offline writer identification and writer verification. The proposed method uses GMM supervectors to encode the feature distribution of individual writers. Each supervector originates from an individual GMM which has been adapted from a background model via a maximum-a-posteriori step followed by mixing the new statistics with the background model. We show that...
We introduce a novel classifier, called max residual classifier (MRC), for learning a sparse representation jointly with a discriminative decision function. MRC seeks to maximize the differences between the residual errors of the wrong classes and the right one. This effectively leads to a more discriminative sparse representation and better classification accuracy. The optimization procedure is simple...
In this paper we propose a highly optimized parallel and distributed BFS on GPU for Graph500 benchmark. We evaluate the performance of our implementation using TSUBAME2.0 supercomputer. We achieve 317 GTEPS (billion traversed edges per second) with scale 35 (a large graph with 34.4 billion vertices and 550 billion edges) using 1366 nodes and 4096 GPUs. With this score, TSUBAME2.0 supercomputer is...
Recently, a video representation based on dense trajectories has been shown to outperform other human action recognition methods on several benchmark datasets. In dense trajectories, points are sampled at uniform intervals in space and time and then tracked using a dense optical flow field. The uniform sampling does not discriminate objects of interest from the background or other objects. Consequently,...
In this paper, we propose a rate distortion optimization based content adaptive transform method for motion compensation residuals. The proposed method utilizes pixel rearrangement to dynamically adjust the transform kernels to adapt to the residual content. Comparing with the traditional adaptive transforms, the highlight of this work is that it obtains the transform kernels from the decoded block,...
The hybrid transform coding scheme that alternates amongst the asymmetric discrete sine transform (ADST) and the discrete cosine transform (DCT) depending on the boundary prediction conditions, is an efficient tool for video and image compression. It optimally exploits the statistical characteristics of prediction residual, thereby achieving significant coding performance gains over the conventional...
We have evaluated the performance of Cauchy Reed-Solomon (CRS) encoding of data blocks with sizes 32 kB to 256 MB. The performance measurements are done on an Intel processor with 4 cores and integrated graphics support. We also used an AMD graphics card in our performance evaluations. Three versions of the CRS algorithm are developed: one sequential version and two OpenCL versions. The OpenCL versions...
Automatic vehicle Make and Model Recognition (MMR) system offers a competent way to vehicle classification and recognition systems. This paper proposes a real time while robust vehicle make and model recognition system extracting the vehicle sub-image from the background and studies some sparse feature coding methods such as Orthogonal Matching Pursuit (OMP), some variation of Sparse Coding (SC) methods...
In information transmission over additive white Gaussian channels with feedback, the use of feedback link to improve the performance of communication systems has been studied by a number of authors. It is well known that the error probability in information transmission can be substantially reduced by using feedback, namely, under the average power constraint, the error probability decreases more...
We propose a fast post filter set for removing coding distortions of depth maps. Lossy coding generates various distortions, such as mosquito and block noises, edge blurs, and over quantization. These distortions seriously deteriorate image quality of synthesized views in free viewpoint image rendering. Thus, we propose the post filter set which includes median filter, Gaussian filter, min-max blur...
In this paper, we propose a content adaptive transform (CAT) method for video coding. Firstly, CAT obtains the transform kernels in real-time instead of predefined fixed ones, and therefore it is content based transform. Secondly, the transform kernels is obtained by singular value decomposition (SVD) from a typical decoded block without transmitting them to the decoder. Thirdly, the optimality property...
The bag of visual words (BoW) model is one of the most successful model in image classification task. However, the major problem of the BoW model lies in the determination of visual words, which consists of codebook training and feature encoding phases. The traditional K-means and hard-assignment method completely ignore the structure of the local feature space, leading to high loss of information...
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.