Forgery operations on video contents are nowadays within the reach of anyone, thanks to the availability of powerful and user-friendly editing software. Integrity verification and authentication of videos represent a major interest in both journalism (e.g., fake news debunking) and legal environments dealing with digital evidence (e.g., a court of law). While several strategies and different forensics traces have been proposed in recent years, latest solutions aim at increasing the accuracy by combining multiple detectors and features. This paper presents a video forgery localization framework that verifies the self-consistency of coding traces between and within video frames, by fusing the information derived from a set of independent feature descriptors. The feature extraction step is carried out by means of an explainable convolutional neural network architecture, specifically designed to look for and classify coding artifacts. The overall framework was validated in two typical forgery scenarios: temporal and spatial splicing. Experimental results show an improvement to the state-of-the-art on temporal splicing localization and also promising performance in the newly tackled case of spatial splicing, on both synthetic and real-world videos.

In this paper, we consider large-scale MIMO systems and we address the channel estimation problem. We propose an iterative receiver consisting of the cascade of a semi-blind least-squares channel estimation algorithm with a simplicity-based detection algorithm for finite-alphabet signals (FAS and FAS-SAC). A minimum number of pilot sequences is used to get an initial channel estimation. The detection algorithm outputs are then used to refine it gradually. Two feeding methods are studied. The first one uses raw detection outputs. The second one is based on hard decisions and enables better performance. Theoretical MSEs are calculated in both cases. Simulations assess the efficiency of the proposed iterative procedure compared to the state-of-the-art methods and show that it performs very close to the ideal scenario where all the communication frame sequences are known.

We present a novel framework for the reconstruction of 1D composite signals assumed to be a mixture of two additive components, one sparse and the other smooth, given a finite number of linear measurements. We formulate the reconstruction problem as a continuous-domain regularized inverse problem with multiple penalties. We prove that these penalties induce reconstructed signals that indeed take the desired form of the sum of a sparse and a smooth component. We then discretize this problem using Riesz bases, which yields a discrete problem that can be solved by standard algorithms. Our discretization is exact in the sense that we are solving the continuous-domain problem over the search space specified by our bases without any discretization error. We propose a complete algorithmic pipeline and demonstrate its feasibility on simulated data.

The papers in this special section focus on applied artificial inteligence and machine learning for video coding and media streaming.

In this paper, we consider a class of nonconvex complex quadratic programming (CQP) problems, which find a broad spectrum of signal processing applications. By using the polar coordinate representations of the complex variables, we first derive a new enhanced semidefinite relaxation (SDR) for problem (CQP). Based on the newly derived SDR, we further propose an efficient branch-and-bound algorithm for solving problem (CQP). Key features of our proposed algorithm are: (1) it is guaranteed to find the global solution of the problem (within any given error tolerance); (2) it is computationally efficient because it carefully utilizes the special structure of the problem. We apply our proposed algorithm to solve the multi-input multi-output (MIMO) detection problem, the unimodular radar code design problem, and the virtual beamforming design problem. Simulation results show that our proposed enhanced SDR, when applied to the above problems, is generally much tighter than the conventional SDR, and our proposed global algorithm can efficiently solve these problems. In particular, our proposed algorithm significantly outperforms the state-of-the-art sphere decode algorithm for solving the MIMO detection problem in the hard cases (where the number of inputs and outputs is equal or the signal-to-noise-ratio is low), and a state-of-the-art general-purpose global optimization solver called Baron for solving the virtual beamforming design problem.

We investigate fusing several unreliable computational units that perform the same task. We model an unreliable computational outcome as an additive perturbation to its error-free result in terms of its fidelity and cost. We analyze reliability of replication-based strategies that distribute cost across several unreliable units and fuse their outcomes. When the cost is a convex function of fidelity, the optimal replication-based strategy in terms of incurred cost while achieving a target mean-square error level may fuse several unreliable computational units. For concave and linear costs, a single more reliable unit incurs lower cost compared to fusion of several lower cost and less reliable units while achieving the same mean-square error level. We show how our results give insight into problems from theoretical neuroscience and circuits.

High power amplifiers (HPA), used at transmission, add nonlinear impairments to the output signals. Through Constant envelope (CE) transmission, distortion in the signal can be avoided without wasting power on PA linearization. A more restricted form of CE transmission, 1-bit quantized transmission, further simplifies the RF chain and reduces the DAC power consumption. In this paper, for CE transmission and 1-bit quantized transmission at the BS antennas, we analyze downlink transmission for low complexity linear precoding. We observe that for small numbers of users in the downlink, correlation among the quantization error components across BS antennas is high, deteriorating the performance rapidly as number of users become smaller. To improve performance for smaller numbers of downlink users, we propose the addition of correlated Gaussian dither to the precoded signal before quantization and subsequent transmission. We observe that the receive SQINR peaks for finite non-trivial dither power. For given value of transmit power, number of BS antennas and number of users, SQINR is maximized analytically by the transmitter, to find the optimum dither power, using the Bussgang decomposition. We observe that with the implementation of optimized dithering, the error floor in the coded BER at high transmit power, for CE and 1-bit quantized transmissions, is pushed down significantly. We also observe that optimum dither power increases monotonically with transmit power, with rate of increase decreasing with increasing transmit power. Further, the optimum dither power strictly increases with number of BS antennas.

Active control of noise for multi-channel applications is affected by the existence of nonlinear primary and secondary paths. There is a degradation in the performance of linear multi-channel active noise control (LMANC) systems based on minimization of sum of squared errors obtained from multiple sensors in presence of nonlinear primary path (NPP) and nonlinear secondary path (NSP) conditions. The NPP and NSP problems are more prominent and challenging for multi-point noise control applications owing to different locations of silent zones and acoustic coupling between secondary sources and error sensors. In order to surmount this problem, an incremental strategy based nonlinear distributed ANC (NDANC) system is developed in this article. The adaptive exponential functional link network (AE-FLN) is employed as an adaptive control unit at the acoustic sensor nodes (ASNs) for the design of NDANC system. The incremental co-operation scheme is utilized to provide uniform noise cancellation in presence of NPP and NSP conditions. Simulation study is conducted extensively to demonstrate the efficiency of the proposed system for different practical NPP and NSP scenarios. The detailed computational load analysis and subjective evaluation of reduction in perceptual noise levels are performed for different real noise conditions.