Recently, deep learning methods have made a significant improvement in compressive sensing image reconstruction task. However, it still remains a problem of block effect which degrades the reconstruction results. In this paper, we propose a fully-convolutional network, where the full image is directly measured with a convolutional layer. Thanks to the overlapped convolutional measurement, the b...

| This paper investigates coding aspects in an OFDM-CDMA environment. The inherent bandwidth expansion in CDMA systems offers many possibilities for the application of powerful codes with low code rates. Three different coding strategies are under consideration: the combination of convolutional and repetition codes (conventional DS-CDMA system), a code-spread system consisting of one very low r...

Yamada, Harashima, and Miyakawa proposed to use a trellis constructed based on a syndrome former for the purpose of Viterbi decoding of rate-(n − 1)/n convolutional codes. In this paper, we extend their code-trellis construction to general rate-k/n convolutional codes. We show that the extended construction is equivalent to the one proposed by Sidorenko and Zyablov. Moreover, we show that the p...

A recursive convolutional encoder can be regarded as an innite impulse response system over the Galois Field of order 2. First, in this paper, we introduce nite response input sequences for recursive convolutional codes that give nite weight output sequences. In practice, we often need to describe the nite response sequence with a certain Hamming weight. Then, di erent properties of nite respon...

In this paper, we investigate pitch contour modelling in speech synthesis based on segmental units. A convolutional pitch target approximation model is proposed. This model allows jointly stochastic modelling of framewise pitch and pitch contour of longer units, of which the intuitive relations are revealed by a convolutional target approximation filter. The pitch contour is stylized by a linea...

In this work we report on progress in integrating deep convolutional features with Deformable Part Models (DPMs). We substitute the Histogram-of-Gradient features of DPMs with Convolutional Neural Network (CNN) features, obtained from the top-most, fifth, convolutional layer of Krizhevsky’s network [8]. We demonstrate that we thereby obtain a substantial boost in performance (+14.5 mAP) when co...

In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN). The objective is to heavily prune convolutional edges while maintaining retrieval performance. To this end, we introduce both data-independent and data-dependent heuristics to prune convolutional edges, and evaluate their performance across various c...

Power line channel often suffers from impulsive interferences generated by electrical appliances. Therefore, power line communication (PLC) suffers the degradation due to such the impulsive interferences. Middleton’s Class A noise model is frequently utilized for the modeling of such the impulsive noise environment. In this paper, we deal with the Viterbi decoding for convolutional code over ad...

Abstract Using algebraic techniques, one of the co-authors has designed a [155,64,20] low density parity check code based on permutation matrices. This code is quasi-cyclic by construction and hence admits a convolutional representation. A set of low density parity check convolutional codes is derived from this quasi-cyclic code and its generalizations. We investigate the performance of these c...

In this paper we will discuss isometries and strong isometries for convolutional codes. Isometries are weight-preserving module isomorphisms whereas strong isometries are, in addition, degree-preserving. Special cases of these maps are certain types of monomial transformations. We will show a form of MacWilliams Equivalence Theorem, that is, each isometry between convolutional codes is given by...