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.
State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to all recorded frames, rendering them computationally demanding and time-consuming and thus limiting their practical use. In contrast, we propose an online (sequential)...
We present a minimalists but effective neural network that computes dense facial correspondences in highly unconstrained RGB images. Our network learns a per-pixel flow and a matchability mask between 2D input photographs of a person and the projection of a textured 3D face model. To train such a network, we generate a massive dataset of synthetic faces with dense labels using renderings of a morphable...
This paper focuses on the task of room layout estimation from a monocular RGB image. Prior works break the problem into two sub-tasks: semantic segmentation of floor, walls, ceiling to produce layout hypotheses, followed by an iterative optimization step to rank these hypotheses. In contrast, we adopt a more direct formulation of this problem as one of estimating an ordered set of room layout keypoints...
Human face exhibits an inherent hierarchy in its representations (i.e., holistic facial expressions can be encoded via a set of facial action units (AUs) and their intensity). Variational (deep) auto-encoders (VAE) have shown great results in unsupervised extraction of hierarchical latent representations from large amounts of image data, while being robust to noise and other undesired artifacts. Potentially,...
Shape reconstruction techniques using structured light have been widely researched and developed due to their robustness, high precision, and density. Because the techniques are based on decoding a pattern to find correspondences, it implicitly requires that the projected patterns be clearly captured by an image sensor, i.e., to avoid defocus and motion blur of the projected pattern. Although intensive...
In this paper we study the initialization step of decoding algorithms for efficient error-control coding techniques, and its dependence of the channel characteristics over which transmission is performed. LDPC and Polar codes are selected as efficient error-control codes operating over different channels. Channels under study are the classic Additive White Gaussian noise channel, the Rayleigh fading...
This study proposes a novel classification method for sequential data invoving human trial and error. The classification of sequential data obtained from human experiments has become an important tool that supports the data analytics of the modern society. For example, several algorithms for motion recognition, voice recognition, etc. have been recently developed. The hidden Markov model (HMM) is...
In this paper, the BER performance of a soft distance successive cancellation decoder for Polar codes is analyzed in the presence of impulsive noise, modelled using both the Middleton's Class A model and the symmetric alpha-stable model, for impulsive noise channels. This algorithm avoids estimation of the signal-to-noise ratio of the channel, and simplifies the initialization step of the classic...
Error correction coding based on soft-input decoding can significantly improve the reliability of flash memories. Such soft-input decoding algorithms require reliability information about the state of the memory cell. This work proposes a channel model for soft-input decoding that considers the asymmetric error characteristic of multi-level cell (MLC) and triple-level cell (TLC) memories. Based on...
The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral representations are then used to derive time-frequency masks. In this work we introduce a method to directly learn time-frequency masks from an observed mixture magnitude...
Document clustering groups documents of certain similar characteristics in one cluster. Document clustering has shown advantages on organization, retrieval, navigation and summarization of a huge amount of text documents on Internet. This paper presents a novel, unsupervised approach for clustering single-author documents into groups based on authorship. The key novelty is that we propose to extract...
In Compressed Sensing, a real-valued sparse vector has to be recovered from an underdetermined system of linear equations. In many applications, however, the elements of the sparse vector are drawn from a finite set. Adapted algorithms incorporating this additional knowledge are required for the discrete-valued setup. In this paper, turbo-based algorithms for both cases are elucidated and analyzed...
Laser phase noise degrades the bit-error-ratio (BER) performance after forward-error correction (FEC), so-called post-FEC BER. In order to suppress phase noise, we introduce iterative decoding between a decoder for carrier-phase estimation and an FEC decoder. The simulation results show that the post-FEC BER performance is improved by 0.8 dB by using the iterative decoder.
With the rapid development of Remote Sensing acquisition techniques, there is a need to scale and improve processing tools to cope with the observed increase of both data volume and richness. Among popular techniques in remote sensing, Deep Learning gains increasing interest but depends on the quality of the training data. Therefore, this paper presents recent Deep Learning approaches for fine or...
In this paper, we investigate the physical-layer network coding (PNC) scheme based on successive interference cancellation (SIC) in multi-way relay channels (MWRC). We consider a scenario where all users simultaneously transmit signals to the relay in the up-link stage while the relay broadcasts a coded message in the down-link stage. In order to extract the network codes from superimposed signals...
Sparse code multiple access (SCMA) is a new type of non-orthogonal modulation suggested for 5G systems offering lower bit-error rate and higher spectral efficiency. There are many challenges when designing high throughput SCMA message passing decoders to meet the standards expected from 5G networks. Particularly, the message passing algorithm (MPA) needs many exponential computations to calculate...
We consider the remote source coding setting in which a source realization is estimated from a lossy compressed sequence of noisy observations. Unlike in the optimal remote source coding problem, however, the encoder is bound to use good codes with respect to the observation sequence, i.e., codes that are optimal for the lossy reconstruction of the observation, rather than the remote source. This...
We consider several related problems of estimating the ‘sparsity’ or number of nonzero elements d in a length n vector x by observing only b = M ⊙ x, where M is a predesigned test matrix independent of x, and the operation ⊙ varies between problems. We aim to provide a Δ-approximation of sparsity for some constant Δ with a minimal number of measurements (rows of M). This framework generalizes multiple...
Automatic translation of natural languages has been an active body of research in the last decades, especially when it comes to statistical translation which uses machine learning algorithms for translation tasks. Machine translation being a key application in the field of natural language processing, it leads to develop many approaches namely, statistical machine translation and recently neural machine...
There is a growing concern regarding the design of decentralized control systems. Witsenhausen's counterexample is a well-known problem which has remained open in this context, and emphasizes the necessity of communication between blocks in a distributed control system. In this paper, we study an infinite vector model of this problem and a new bound for the cost function is derived. It is shown that...
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.