In this letter, we are proposing $Bo$ CNN architecture framework for occluded thermal face recognition. We analyzed the performance of Pretrained models using transfer learning and they exhibit promising results for thermal faces without occlusion. The performance degrades with occlusion. We have used different decision level fusion strategies post transfer learning for the performance enhancement

A fast and effective image fusion method based on discrete cosine transform (DCT) is proposed. The fusion quality and computation time of current DCT-based image fusion methods largely depend on the selected block size, and the selection of the block size is very difficult in practice. A novel image fusion method based on DCT coefficient matrix features is proposed, which can effectively overcome the

This paper develops a framework for the design of diffusion adaptive algorithms, where a network of nodes aim to estimate system parameters from the collected distinct local data stream. We explore the time and spatial knowledge of system responses and model their evolution in both time and spatial domain. A weighted maximum a posteriori probability (MAP) is used to derive an adaptive estimator, where

In this letter, we propose a novel conjugate gradient (CG) adaptive filtering algorithm for online estimation of system responses that admit sparsity. Specifically, the Sparsity-promoting Conjugate Gradient (SCG) algorithm is developed based on iterative reweighting methods popular in the sparse signal recovery area. We propose an affine scaling transformation strategy within the reweighting framework

Analytic dynamic models for target estimation are often approximations of the potentially complex behaviour of the object of interest. Its true motion might depend on hundreds of parameters and can involve long-term temporal correlation. However, conventional models keep the degrees of freedom low and they usually assume the Markov property to reduce computational complexity. In particular, the Kalman

Pixel-value-ordering (PVO) is a widely used reversible data hiding (RDH) framework which aims to achieve the high quality of stego-image under low capacity. In this letter, we propose a general location-based adaptive complexity for PVO. Different from the block-based complexity in the previous PVO-based methods, our proposed method adaptively selects context pixels from the perspective of the relative

This letter proposes new estimations of fractional power spectral density (FrPSD) and fractional correlation function (FrCF) for nonuniform sampling of random signals with non-stationarity and limited bandwidths in the fractional Fourier domain. Unlike previous works, the developed FrPSD and FrCF estimations are capable of dealing with unknown sampling instants. In order to obtain them, we first formulate

In this paper, we introduce a novel time-frequency technique for the retrieval of the modes of multicomponent signals based on linear chirp approximation. The key idea to this new technique is to design the retrieval procedure by using only information extracted in the vicinity of the ridges made by the components in the time-frequency plane. Compared with state-of-the-art methods based on time-frequency

Support recovery from multiple measurement vectors has been regarded as a critical aspect of compressive sensing. Most existing recovery algorithms require the prior knowledge of the sparsity or the noise power, which are unknown or even time-varying in actual applications, to determine the termination condition of the iterative recovery process. Motivated by the entropy concept from information theory

One of the major challenges in multivariate analysis is the estimation of population covariance matrix from the sample covariance matrix (SCM). Most recent covariance matrix estimators use either shrinkage transformations or asymptotic results from Random Matrix Theory (RMT). Both of these techniques try to achieve a similar goal which is to remove noisy correlations and add structure to SCM to overcome

In the stereo matching networks based on deep learning, current cost aggregation networks lack the means to aggregate cost volume to the utmost extent. Therefore, different from the standard encoder-decoder structures, we propose an attention aggregation encoder-decoder network framework for stereo matching that contains three modules. Specifically, we design a sub-branch and cross-stage aggregation

This paper deals with constant modulus waveform design in spectrally dense environments assuming a discrete phase code alphabet. The goal is to optimize the radar detection performance while rigorously controlling the injected interference energy within each shared band and enforcing a similarity constraint to manage some relevant signal features. To tackle the resulting NP-hard optimization problem

With the rapidly growing number of security-sensitive systems that use voice as the primary input, it becomes increasingly important to address these systems’ potential vulnerability to replay attacks. Previous efforts to address this concern have focused primarily on single-channel audio. In this paper, we introduce a novel neural network-based replay attack detection model that further leverages

In this letter, we propose a sparse array design method for adaptive beamforming in the presence of interferences. Our solution is based on finding the beamformer weight vector such that maximum output signal-to-interference-plus-noise ratio is attained. To control the sidelobes of the beampattern, quadratic fractional constraints are also introduced to optimize the beamformer weights. We formulate

Many applications generate data with an intrinsic network structure such as time series data, image data or social network data. The network Lasso (nLasso) has been proposed recently as a method for joint clustering and optimization of machine learning models for networked data. The nLasso extends the Lasso from sparse linear models to clustered graph signals. This paper explores the duality of nLasso

The fundamental multidimensional line spectral estimation problem is addressed utilizing the Bayesian methods. Motivated by the recently proposed variational line spectral estimation (VALSE) algorithm, multidimensional VALSE (MDVALSE) is developed. MDVALSE inherits the advantages of VALSE such as automatically estimating the model order, noise variance and providing uncertain degrees of frequency estimates

Convolutional networks have achieved the state-of-the-art performance on Acoustic Scene Classification (ASC). Given the Log Mel-Spectrogram of an audio sample, the network can extract useful semantic contents in a certain range receptive field by stacking local convolutional operations. However, the temporal relations between different receptive fields are not captured explicitly. In this letter, we

In this letter, we first propose a novel coding method to design content-adaptive H.264 steganography with quantized discrete cosine transform (QDCT) coefficients. Currently, the state-of-the-art steganographic methods minimize a heuristically defined distortion function using STCs and embed messages in a pixel-wise manner. When this concept is directly applied to H.264 steganographic designing, there

The use of Reinforcement Learning (RL) approaches for dialogue policy optimization has been the new trend for dialogue management systems. Several methods have been proposed, which are trained on dialogue data to provide optimal system response. However, most of these approaches exhibit performance degradation in the presence of noise, poor scalability to other domains, as well as performance instabilities

This letter proposes a method to obtain integer reversible discrete cosine transforms for generic transform-based coding schemes. The novelty of the proposed method, which is based on decomposition of the DCT-II matrix into two triangular and one diagonal matrices, is twofold: (i) the new matrices can be of arbitrary size, i.e., any square $N\times N$ dimension, thus suitable for applications where

We study a variational formulation for reconstructing nonlinearly distorted signals corrupted with a Poisson-Gaussian noise. In this situation, the data fidelity term consists of a sum of a weighted least squares term and a logarithmic one. Both of them are precomposed by a nonlinearity, modelling a clipping effect, which is assumed to be rational. A regularization term, being a piecewise rational

Very fast image and video codecs are a pursued goal both in the academia and the industry. This paper presents a complexity scalable and parallel bitplane coding engine for wavelet-based image codecs. The proposed method processes the coefficients in parallel, suiting hardware architectures based on vector instructions. Our previous work is extended with a mechanism that provides complexity scalability

In this letter, we consider channel estimation for intelligent reflecting surface (IRS)-assisted millimeter wave (mmWave) systems, where an IRS is deployed to assist the data transmission from the base station (BS) to a user. It is shown that for the purpose of joint active and passive beamforming, the knowledge of a large-size cascade channel matrix needs to be acquired. To reduce the training overhead

Generative adversarial networks (GANs) have shown remarkable success in the generation of data from natural data manifolds such as images. In several scenarios, it is desirable that generated data is well-clustered, especially when there is severe class imbalance. In this paper, we focus on the problem of clustering in the generated space of GANs and uncover its relationship with the characteristics

Multichannel audio blind source separation (BSS) in the determined situation (the number of microphones is equal to that of the sources), or determined BSS, is performed by multichannel linear filtering in the time-frequency domain to handle the convolutive mixing process. Ordinarily, the filter treats each frequency independently, which causes the well-known permutation problem , i.e., the problem

This letter presents a convolutional neural network (CNN) for image denoising, especially for the reduction of real noises. As a network topology, we adopt the dual path network (DPN) that combines the advantages of residual and densely connected networks. Using the DPN as a basic building block, we design a network that connects the DPN in dual path again with an attention mechanism. For efficient

A novel method for active speaker detection and localization in audio-visual recordings is proposed. The method relies on a specifically tailored matrix decomposition that exploits the intrinsic low-dimensional structure of audio-visual data, namely, the low-rank of the background visual/audio information and the sparsity of the correlated foreground components. Concretely, the data matrix of each

Existing trajectory data reconstruction algorithms for tracking, telemetry, and command (TT&C) channel simulators cannot achieve continuity and noise reduction simultaneously. By combining the B-spline interpolation algorithm with the least-square (LS) approximation algorithm, we propose a novel trajectory data reconstruction algorithm using LS B-spline approximation. In addition, a polyphase structure

Due to projective transformation, a great variety of pedestrian sizes appears on the image depending on their depths in the real world. In this letter, we analyze the object proposal generation strategies in existing object detection methods that underperform in some real-world applications owing to ignorance of spatial factors. To this end, we propose a neural network predictor to estimate the sizes

Inspired by the great success of the deep neural networks in various fields of computer vision, studies for image deblurring have begun to become more active in recent days. However, most previous approaches often fail to accurately remove the blur artifacts, e.g., ghosting effects at the object boundaries and degradation of local details, in restored results. In this paper, we propose a deep spectral-spatial

Image colorization based on numerical modeling gives a highly accurate restoration result when colors are given to enough regions. A lot of numerical models focus on the relation between adjacent pixels; therefore, it is required to give the same color to various regions, and high spatial frequency regions are not colored properly. This letter proposes a colorization algorithm using graph signal processing

To ensure signal receiving quality, robust adaptive beamforming (RAB) is of vital importance in modern communications. In this letter, we propose a new low-complexity RAB approach based on interference-plus-noise covariance matrix (IPNC) reconstruction and steering vector (SV) estimation. In this method, the IPNC and desired signal covariance matrices are reconstructed by estimating all interference

Learning part-based features with multiple branches has been proven as an effective way to deliver high performance person re-identification. Existing works mostly exploit extra constraints on different branches to ensure the diversity of extracted features, which may lead to the increased complexity in network architecture and the difficulty for training. In this letter, we propose a quite simple

In communications and radar/sonar systems, one of the most popular nonstationary stochastic signal models is the chirp cyclostationary (CCS) signal. Recently, the second-order statistics of complex CCS signals are defined based on the conjugate correlation function, which have shown to be more proper in linear canonical transform domain than in the frequency domain. However, the information provided

Deep convolutional neural networks (CNNs) have become the tool of choice for steganalysis because they outperform older feature-based detectors by a large margin. However, recent work points at cases where feature-based detectors perform better than CNNs due to their failure to compute simple statistics of DCT coefficients. We introduce a shallow “OneHot” CNN, which encodes DCT coefficients using clipped

In this letter, a novel approach to construct virtual array is proposed by exploiting synthetic aperture technology and the concept of difference coarray for sparse arrays. First, we prove that the proposed method can increase the degrees of freedom (DOF) of an arbitrary moving sparse array threefold. Therefore, the maximal number of resolvable sources for direction-of-arrival (DOA) estimation is tripled

The performance of recent RGB-D salient object detectors has significantly improved owing to their integration of convolutional neural networks (CNNs). However, most existing salient object detection (SOD) methods represent features using a VGGNet backbone, which lacks the ability to retain complete RGB and depth modals and must compensate by applying several skip connections. In this letter, we propose

In recent years, the Kalman filter has become the prime approach for estimating parameters that evolve following some dynamic model and prior statistics. In addition, recent contributions are introducing the use of autoregressive models in the state-space formulation to deal with correlated Gaussian-distributed magnitudes. However, the derivation of closed-form expressions for predicting their performance

Automated decision making is used routinely throughout our every-day life. Recommender systems decide which jobs, movies, or other user profiles might be interesting to us. Spell checkers help us to make good use of language. Fraud detection systems decide if a credit card transactions should be verified more closely. Many of these decision making systems use machine learning methods that fit complex

Automatic modulation classification facilitates many important signal processing applications. Recently, deep learning models have been adopted in modulation recognition, which outperform traditional machine learning techniques based on hand-crafted features. However, automatic modulation classification is still challenging due to the following reasons. Existing deep learning methods are only applicable

We consider a separation problem where the observation consists of the sum of a high amplitude smooth signal and a low amplitude transient signal. We propose a method for decomposition that relies on solving instances of a ‘constrained filtering problem,’ which is posed as a convex minimization problem. We provide a fast algorithm for solving the minimization problem, and demonstrate the potential

We propose a 4-dimensional (4D) basis and sampling scheme, along with a corresponding reconstruction algorithm, for the measurement and reconstruction of the $\mathbf {b}$ -tensor encoded diffusion signal in diffusion magnetic resonance imaging (MRI). This is only the second basis proposed for representing the $\mathbf {b}$ -tensor encoded diffusion signal and the first to allow for planar tensor measurements

We consider adaptive detection of a signal of interest when two sets of training samples are available, one sharing the same covariance matrix as the data under test, the other set being mismatched. The approach proposed in this letter is to whiten both the data under test and the matched training samples using the sample covariance matrix of the mismatched training samples. The distribution of the

This letter deals with the robust joint design of radar transmit waveform and receive filter bank in a background of range unambiguous signal-dependent clutter. Assuming an unknown Doppler shift for the target, the worst-case Signal-to-Interference-plus-Noise-Ratio (SINR) at the output of the receive filter bank is considered as the figure of merit. The transceiver design is pursued considering a max-min

We introduce negative binomial matrix factorization (NBMF), a matrix factorization technique specially designed for analyzing over-dispersed count data. It can be viewed as an extension of Poisson factorization (PF) perturbed by a multiplicative term which models exposure. This term brings a degree of freedom for controlling the dispersion, making NBMF more robust to outliers. We describe a majorization-minimization

The low-rank tensor factorization (LRTF) technique has received increasing popularity in data science, especially in computer vision applications. Many robust LRTF models have been presented recently. However, none of them take the skewness of data into account. This letter proposes a novel LRTF model for skew data analysis by modeling noise as a Mixture of Asymmetric Laplacians (MoAL). The numerical

Ramanujan filter banks have been used for identifying periodicity structure in streaming data. This letter studies the locations of zeros of Ramanujan filters. All the zeros of Ramanujan filters are shown to lie on or inside the unit circle in the $z$ -plane. A convenient factorization appears as a corollary of this result, which is useful to identify common factors between different Ramanujan filters

In this paper, the problem of time series reconstruction in a multiway delay embedded space using Tensor Train decomposition is addressed. A new algorithm has been developed in which an incomplete signal is first transformed to a Hankel matrix and in the next step to a higher order tensor using extended Multiway Delay embedded Transform. Then, the resulting higher order tensor is completed using low

Phase retrieval algorithms are now an important component of many modern computational imaging systems. A recently proposed scheme called generalized expectation consistent signal recovery (GEC-SR) shows better accuracy, speed, and robustness than numerous existing methods. Decentralized GEC-SR (deGEC-SR) addresses the scalability issue in high-resolution images. However, the convergence speed and

We study the problem of distributed estimation over adaptive networks where communication delays exist between nodes. In particular, we investigate the diffusion Least-Mean-Square (LMS) strategy where delayed intermediate estimates (due to the communication channels) are employed during the combination step. One important question is: Do the delays affect the stability condition and performance? To

This letter proposes a new time domain absorption approach designed to reduce masking components of speech signals under noisy-reverberant conditions. In this method, the nonstationarity of corrupted signal segments is used to detect masking distortions based on a defined threshold. The non-stationarity is objectively measured and is also adopted to determine the absorption procedure. Additionally

This letter presents a high resolution method which separates close components of a multi-component linear frequency modulated (LFM) signal and eliminates their Cross-Terms (CTs). We first investigate the energy distribution of the Auto-Terms (ATs) and CTs in ambiguity plane. This reveals that the energy of the CTs of parallel close components is significant around the origin. We propose to mask the

This correspondence proposes the use of a real-only equalizer (ROE), which acts on real signals derived from the received offset quadrature amplitude modulation (OQAM) symbols. For the same fading channel, we prove that both ROE and the widely linear equalizer (WLE) yield equivalent outputs. Hence, these exhibit the same performance. Our complexity analysis finds that depending on the frame length

In this letter, we derive the exact joint probability density function (pdf) of the amplitude and phase of the product of two correlated non-zero mean complex Gaussian random variables with arbitrary variances. This distribution is useful in many problems, for example radar and communication systems. We determine the joint pdf in terms of an infinite summation of modified Bessel functions of the first

In this letter, a deep-learning based method is proposed for signal sequence detection. A novel neural network (NN) architecture, in communications systems called Cooperative and Time-varying Bidirectional Recurrent Neural Network (CTBRNN), is developed, which learns from the training data and estimates the transmitted signal sequence without knowing the underlying channel model. Furthermore, we develop

Utilizing a human-perception-related objective function to train a speech enhancement model has become a popular topic recently. The main reason is that the conventional mean squared error (MSE) loss cannot represent auditory perception well. One of the typical human-perception-related metrics, which is the perceptual evaluation of speech quality (PESQ), has been proven to provide a high correlation

Developing Semi-Supervised Seq2Seq (S4) learning for sequence transduction tasks in natural language processing (NLP), e.g. semantic parsing, is challenging, since both the input and the output sequences are discrete. This discrete nature makes trouble for methods which need gradients either from the input space or from the output space. Recently, a new learning method called joint stochastic approximation

In this letter, we propose a new approach to tracking a target that maneuvers based on the multiple-constant-turns model. Usually, the interactive-multiple-model (IMM) algorithm based on the extended Kalman filter (IMM-EKF) is employed for this problem with successful tracking performance. Recently proposed IMM-particle filtering (IMM-PF) showed outperforming results over IMM-EKF for this nonlinear

Image non-blind deblurring is still an ill-posed problem. Uncertainty in solutions occurs when singular vectors of forward model matrix spanning the noise subspace have rather small singular values. This letter proposes a new image deblurring algorithm, called MNBC-Gibbs (multiple norms and boundary constraint enforced Gibbs sampling). To be more specific, the quadratic and sparseness-inducing norms

The population Monte Carlo (PMC) algorithm is a powerful adaptive importance sampling (AIS) methodology used for estimating expected values of random quantities w.r.t. some target probability distribution. At each iteration, a Markov transition kernel is used to propagate a set of particles. Importance weights of the particles are computed and then used to resample the particles that are most representative