Presents the front cover for this issue of the publication.

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Presents the table of contents for this issue of the publication.

The emergence of big data and the multidimensional nature of wireless communication signals present significant opportunities for exploiting the versatility of tensor decompositions in associated data analysis and signal processing. The uniqueness of tensor decompositions, unlike matrix-based methods, can be guaranteed under very mild and natural conditions. Harnessing the power of multilinear algebra

Multidimensional signals like multispectral images and color videos are becoming ubiquitous in modern times, constantly introducing challenges in data storage and transfer, and therefore demanding efficient compression strategies. Such high dimensional observations can be naturally encoded as tensors, exhibiting significant redundancies across dimensions. This property is exploited by tensor decomposition

Unlike traditional tensor decompositions which model low-rankness in the original domain, the recently proposed tensor $*_L$ -Singular Value Decomposition ( $*_L$ –SVD) casts a new light on tensor analysis by exploiting low-rankness in the spectral domain. For convexized rank minimization within the framework of $*_L$ –SVD, the tensor $*_L$ –Tubal Nuclear Norm ( $*_L$ –TNN) outperforms classical tensorial

Multidimensional data have become ubiquitous and are frequently encountered in situations where the information is aggregated over multiple data atoms. The aggregation can be over time or other features, such as geographical location. We often have access to multiple aggregated views of the same data, each aggregated in one or more dimensions, especially when data are collected or measured by different

Structured Tucker tensor decomposition models complete or incomplete multiway data sets (tensors), where the core tensor and the factor matrices can obey different constraints. The model includes block-term decomposition or canonical polyadic decomposition as special cases. We propose a very flexible optimization method for the structured Tucker decomposition problem, based on the second-order Levenberg-Marquardt

Tucker decomposition is a standard method for processing multi-way (tensor) measurements and finds many applications in machine learning and data mining, among other fields. When tensor measurements arrive in a streaming fashion or are too many to jointly decompose, incremental Tucker analysis is preferred. In addition, dynamic adaptation of bases is desired when the nominal data subspaces change.

In the recent years, we have witnessed an explosion of networking applications due to the reasons such as the rapid development of cloud infrastructure, edge computing, and the Internet of Things. Furthermore, those applications become complex, the problem related to the large size of the state space and limited metric collection has emerged. This leads to an urging demand for adaptive management method

CNNs achieve high levels of performance by leveraging deep, over-parametrized neural architectures, trained on large datasets. However, they exhibit limited generalization abilities outside their training domain and lack robustness to corruptions such as noise and adversarial attacks. To improve robustness and obtain more computationally and memory efficient models, better inductive biases are needed

Blind deconvolution and demixing is the problem of reconstructing convolved signals and kernels from the sum of their convolutions. This problem arises in many applications, such as blind MIMO. This work presents a separable approach to blind deconvolution and demixing via convex optimization. Unlike previous works, our formulation allows separation into smaller optimization problems, which significantly

Light field image (LFI) collects radiance from rays in different directions, offers powerful capabilities for immersive media and computer vision. As the high-dimensional data, LFI suffers from spatial as well as angular information distortions in its processing, which brings new challenges to image quality assessment (IQA). Based on the strong ability of tensor about representing high-dimensional

Coupled tensor approximation has recently emerged as a promising approach for the fusion of hyperspectral and multispectral images, reconciling state of the art performance with strong theoretical guarantees. However, tensor-based approaches previously proposed assume that the different observed images are acquired under exactly the same conditions. A recent work proposed to accommodate inter-image

Several methods based on Total Variation (TV) have been proposed for Hyperspectral Image (HSI) denoising. However, the TV terms of these methods just use various $l_1$ norms and penalize image gradient magnitudes, having a negative influence on the preprocessing of HSI denoising and further HSI classification task. In this paper, a novel $l_0$ Total Variation ( $l_0$ TV) is first introduced and analyzed

Recurrent neural networks, especially the convolutional long short-term memory (ConvLSTM), have attracted plenty of attention and shown promising results due to their ability in modeling long-term dependencies in many research fields. In this paper, a lightweight tensor attention-driven ConvLSTM neural network (TACLNN) is proposed for hyperspectral image (HSI) classification. Firstly, to reduce the

To better understand the genes with altered expression caused by infection with the novel coronavirus strain SARS-CoV-2 causing COVID-19 infectious disease, a tensor decomposition (TD)-based unsupervised feature extraction (FE) approach was applied to a gene expression profile dataset of the mouse liver and spleen with experimental infection of mouse hepatitis virus, which is regarded as a suitable

In this paper, a data-driven position-aided approach is proposed to reduce the training overhead in MIMO systems by leveraging side information and on-the-field measurements. A data tensor is constructed by collecting beam-training measurements on a subset of positions and beams, and a hybrid noisy tensor completion (HNTC) algorithm is proposed to predict the received power across the coverage area

Intelligent reflecting surface (IRS) is an emerging technology for future wireless communications including 5G and especially 6 G. It consists of a large 2D array of (semi-)passive scattering elements that control the electromagnetic properties of radio-frequency waves so that the reflected signals add coherently at the intended receiver or destructively to reduce co-channel interference. The promised

Phase-noise is a system impairment caused by the mismatch between the oscillators at the transmitter and the receiver. In OFDM systems, this induces inter-carrier-interference (ICI) by rotating the transmitted symbols. Thus it can cause severe system performance degradation. To reduce its effects, the phase-noise must be estimated or compensated. In this work, we propose a two-stage tensor-based receiver

In this paper, we present a gridless channel estimation algorithm for a hybrid millimeter wave (mmWave) MIMO-OFDM system assuming a frequency-selective channel. The proposed algorithm is based on the Tensor-ESPRIT in DFT beamspace algorithm framework. First, we derive the $R$ -dimensional ( $R$ -D) Standard/Unitary Tensor-ESPRIT in DFT beamspace framework and its analytic performance. We show that

Channel estimation has long been deemed as one of the most critical problems in three-dimensional (3D) massive multiple-input multiple-output (MIMO), which is recognized as the leading technology that enables 3D spatial signal processing in the fifth-generation (5G) wireless communications and beyond. Recently, by exploring the angular channel model and tensor decompositions, the accuracy of single-user

In this paper, we develop solutions for sparse tensor signal recovery (SR) and tensor dictionary learning (DL) problems via the sparse Bayesian learning (SBL) approach. We consider a class of tensor system which has the special sparsity structure that a given (say the $i$ th) row of every unfolding matrices of the tensor involved is simultaneously zero or non-zero. For both problems, we propose a Kronecker-like

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Presents the front cover for this issue of the publication.

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Presents the front cover for this issue of the publication.

The papers in this special issue focus on deep learning for image/video restoration and compression. The huge success of deep-learning–based approaches in computer vision has inspired research in learned solutions to classic image/video processing problems, such as denoising, deblurring, dehazing, deraining, super-resolution (SR), and compression. Hence, learning-based methods have emerged as a promising

Image restoration remains a challenging task in image processing. Numerous methods tackle this problem, which is often solved by minimizing a nonsmooth penalized co-log-likelihood function. Although the solution is easily interpretable with theoretic guarantees, its estimation relies on an optimization process that can take time. Considering the research effort in deep learning for image classification

Image degradation due to atmospheric turbulence (AT), which is common while capturing images at long ranges, adversely affects the performance of tasks such as face alignment and face recognition. To the best of our knowledge, there does not exist any dataset consisting of turbulence-degraded face images along with their annotated landmarks and ground-truth clean images, making supervised training

Recently, an increasing number of algorithms have been proposed for rain streak removal. However, most existing methods ignore the discrepancy in removing rain streaks from background contents with different texture richness (frequencies). They adopt a unified scheme to learn the final distribution of rain streaks directly, thus sacrificing the representative accuracy of rain information. To this end

Deep neural networks have achieved remarkable success in single image super-resolution (SISR). However, in most cases, image SR with different scale factors is considered as different tasks and solved by training specific models. It makes the image SR applications inefficient and tedious. Hence, to tackle these problems, we propose a lightweight and fast network (MSWSR) to implement multi-scale SR

Multi–grid back–projection (MGBP) is a fully–convolutional network architecture that can learn to restore images and videos with upscaling artifacts. Using the same strategy of multi–grid partial differential equation (PDE) solvers this multiscale architecture scales computational complexity efficiently with increasing output resolutions. The basic processing block is inspired in the iterative back–projection

Blind hyperspectral unmixing is an important technique in hyperspectral image analysis, aiming at estimating endmembers and their respective fractional abundances. Consider the limitations of using the linear model, nonlinear unmixing methods have been studied under different model assumptions. However, existing nonlinear unmixing algorithms do not fully exploit spectral and spatial correlation information

Completing a corrupted image by filling in correct structures and reasonable textures for a complex scene remains an elusive challenge. In case that a missing hole involves diverse semantic information, conventional two-stage approaches based on structural information often lead to unreliable structural prediction and ambiguous visual texture generation. To address the problem, we propose a SEmantic

The current gold standard in solving image processing and computer vision tasks is using supervised learning of deep neural networks (DNNs), requiring large-scale datasets of input-output pairs. In many scenarios in which the output is an image – e.g., medical image analysis, image denoising, deblurring, super-resolution, dehazing, segmentation and optical flow estimation – the collection of labelled

Point clouds are an increasingly relevant geometric data type but they are often corrupted by noise and affected by the presence of outliers. We propose a deep learning method that can simultaneously denoise a point cloud and remove outliers in a single model. The core of the proposed method is a graph-convolutional neural network able to efficiently deal with the irregular domain and the permutation

Point clouds are a very rich 3D visual representation model, which has become increasingly appealing for multimedia applications with immersion, interaction and realism requirements. Due to different acquisition and creation conditions as well as target applications, point clouds’ characteristics may be very diverse, notably on their density. While geographical information systems or autonomous driving

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Dynamic range limitations in signal processing often lead to clipping, or saturation, in signals. The task of audio declipping is estimating the original audio signal, given its clipped measurements, and has attracted much interest in recent years. Audio declipping algorithms often make assumptions about the underlying signal, such as sparsity or low-rankness, and about the measurement system. In this

Clipping is a common type of distortion in which the amplitude of a signal is truncated if it exceeds a certain threshold. Sparse representation has underpinned several algorithms developed recently for reconstruction of the original signal from clipped observations. However, these declipping algorithms are often built on a synthesis model, where the signal is represented by a dictionary weighted by

Phase retrieval (PR) aims to recover a signal from the magnitudes of a set of inner products. This problem arises in many audio signal processing applications which operate on a short-time Fourier transform magnitude or power spectrogram, and discard the phase information. Recovering the missing phase from the resulting modified spectrogram is indeed necessary in order to synthesize time-domain signals

In this paper, we address a particular instance of time-frequency filter design, which we call Time-Frequency Fading (TFF). In TFF the only available information concerns the time-frequency localization of the component to be filtered out or attenuated: the signal of interest is supposed to be spread out in the time-frequency plane, whereas the perturbation signal is concentrated within a specified

The objective of audio inpainting is to fill a gap in an audio signal. This is ideally done by reconstructing the original signal or, at least, by inferring a meaningful surrogate signal. We propose a novel approach applying sparse modeling in the time-frequency (TF) domain. In particular, we devise a dictionary learning technique which learns the dictionary from reliable parts around the gap with

Deep neural networks based methods dominate recent development in single channel speech enhancement. In this paper, we propose a multi-scale feature recalibration convolutional encoder-decoder with bidirectional gated recurrent unit (BGRU) architecture for end-to-end speech enhancement. More specifically, multi-scale recalibration 2-D convolutional layers are used to extract local and contextual features

This paper proposes a novel tensor-train deep neural network (TT-DNN) based channel estimator to tackle challenges of time-varying channel estimation in multiple-input multiple-output (MIMO) systems. A centralized DNN channel estimator can be realized by a distributed TT-DNN with parallel paths. The TT-DNN provides a compact representation by decomposing each DNN layer into a TT format with fewer model

Tensor network and tensor computation are widely applied in scientific and engineering domains like quantum physics, electronic design automation, and machine learning. As one of the most fundamental operations for tensor networks, a tensor contraction eliminates the sharing orders among tensors and produces a compact sub-network. Different contraction sequence usually yields distinct storage and compute

Optimal rank selection is an important issue in tensor decomposition problems, especially for Tensor Train (TT) and Tensor Ring (TR) (also known as Tensor Chain) decompositions. In this paper, a new rank selection method for TR decomposition has been proposed for automatically finding near-optimal TR ranks, which result in a lower storage cost, especially for tensors with inexact TT or TR structures

The so-called block-term decomposition (BTD) tensor model has been recently receiving increasing attention due to its enhanced ability of representing systems and signals that are composed of blocks of rank higher than one, a scenario encountered in numerous and diverse applications. Its uniqueness and approximation have thus been thoroughly studied. Nevertheless, the challenging problem of estimating

Hyperspectral super-resolution (HSR) aims at fusing a pair of hyperspectral and multispectral images to recover a super-resolution image (SRI). This work revisits coupled tensor decomposition (CTD)-based HSR. The vast majority of the HSR approaches take a low-rank matrix recovery perspective. The challenge is that theoretical guarantees for recovering the SRI using low-rank matrix models are either

The canonical polyadic decomposition (CPD) allows one to extract compact and interpretable representations of tensors. Several optimization-based methods exist to fit the CPD of a tensor for the standard least-squares (LS) cost function. Extensions have been proposed for more general cost functions such as $\beta$ -divergences as well. For these non-LS cost functions, a generalized Gauss–Newton (GGN)

Coupled matrix and tensor factorizations (CMTF) are frequently used to jointly analyze data from multiple sources, a task also called data fusion. However, different characteristics of datasets stemming from multiple sources pose many challenges in data fusion and require to employ various regularizations, constraints, loss functions and different types of coupling structures between datasets. In this

In this article, we introduce a dynamic generative model, the Bayesian allocation model (BAM), for modeling count data. BAM covers various probabilistic nonnegative tensor factorization (NTF) and topic models under one general framework. In BAM, allocations are made using a Bayesian network, whose conditional probability tables can be integrated out analytically. We show that, when allocations are

Neural networks can be successfully used to improve several modules of advanced video coding schemes. In particular, compression of colour components was shown to greatly benefit from usage of machine learning models, thanks to the design of appropriate attention-based architectures that allow the prediction to exploit specific samples in the reference region. However, such architectures tend to be

Divide and conquer is an established algorithm design paradigm that has proven itself to solve a variety of problems efficiently. However, it is yet to be fully explored in solving problems with a neural network, particularly the problem of image super-resolution. In this work, we propose an approach to divide the problem of image super-resolution into multiple subproblems and then solve/conquer them

Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this paper, we present a new approach suitable for handling the image-specific and spatially-varying nature of degradation in images affected by practically occurring artifacts

In this paper, we propose a novel convolutional neural network (CNN) architecture, MFRNet, for post-processing (PP) and in-loop filtering (ILF) in the context of video compression. This network consists of four multi-level feature review residual dense blocks (MFRBs), which are connected using a cascading structure. Each MFRB extracts features from multiple convolutional layers using dense connections

The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully exploit the temporal correlation among video frames. To overcome this shortcoming, this paper proposes a Recurrent Learned Video Compression (RLVC) approach with

Image restoration is a critical component of image processing pipelines and for low-level computer vision tasks. Conventional image restoration approaches are mostly based on hand-crafted image priors. The inter-channel correlation of color images is not fully exploited. Motivated by the special characteristics of the inter-channel correlation (higher correlation for red/green and green/blue channels

This paper presents a new framework for severely distorted image and video recovery via tensor augmentation and completion. By considering the task of representing a matrix by a high-order- $n$ tensor as that of encoding the matrix's 2-D indices $(i,j)$ by $n$ -digit words $i_1i_2\dots i_n$ , we develop a new high order tensor augmentation to cast a third order tensor of color images or video sequences