We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training SpatioTemporal ConvNets from scratch. We describe several initializations of weights in 3D Convolutional Layers of Spatio-Temporal ConvNet using 2D Convolutional Weights learned from ImageNet. We show that it is important to i...

While convolutional sparse representations enjoy a number of useful properties, they have received limited attention for image reconstruction problems. The present paper compares the performance of block-based and convolutional sparse representations in the removal of Gaussian white noise. While the usual formulation of the convolutional sparse coding problem is slightly inferior to the block-b...

It is well known that a convolutional code is essentially a linear system def ined over a finite field. In this paper we elaborate on this connect ion. W e will def ine a convolutional code as the dual of a complete linear behavior in the sense of W illems. Using ideas from systems theory, we descr ibe a set of general ized first-order descriptions for convolutional codes. As an application of ...

Convolutional codes over rings are particularly suitable for representing codes over phase modulation signals. In order to develop a complete structural analysis of this class of codes, it is necessary to study rational matrices over rings, which constitutes the generator matrices (encoders) for such convolutional codes. Noncatastrophic, minimal, systematic and basic generator matrices are intr...

Forward Error Correction (FEC) schemes are an essential component of wireless communication systems. Convolutional codes are employed to implement FEC but the complexity of corresponding decoders increases exponentially according to the constraint length. Present wireless standards such as Third generation (3G) systems, GSM, 802.11A, 802.16 utilize some configuration of convolutional coding. Co...

Forward Error Correction (FEC) schemes are an essential component of wireless communication systems. Convolutional codes are employed to implement FEC but the complexity of corresponding decoders increases exponentially according to the constraint length. Present wireless standards such as Third generation (3G) systems, GSM, 802.11A, 802.16 utilize some configuration of convolutional coding. Co...

In this paper, we propose a novel method to construct low rate recursive convolutional codes. The ‘overall’ convolutional code has a block code and a simple recursive convolutional code as building blocks. The novelty of this type of convolutional code is that it uses coset leaders in order to distinguish the signals that originate from different states. Several of these codes are then used to ...

Successful fine-grained image classification methods learn subtle details between visually similar (sub-)classes, but the problem becomes significantly more challenging if the details are missing due to low resolution. Encouraged by the recent success of Convolutional Neural Network (CNN) architectures in image classification, we propose a novel resolution-aware deep model which combines convol...

Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically composing simple local features into complex models. We try to apply the conv...

In this paper we demonstrate that among all subspaces of GF(q) ! convolutional codes are best suited for error control purposes. To this end we regard several deening properties of convolutional codes and study the classes of subspaces deened by each of those properties alone. It turns out that these superclasses of the class of convolutional codes either achieve no better distance to rate rati...