SPL Articles

Adaptive importance sampling (AIS) methods provide a useful alternative to Markov Chain Monte Carlo (MCMC) algorithms for performing inference of intractable distributions. Population Monte Carlo (PMC) algorithms constitute a family of AIS approaches which adapt the proposal distributions iteratively to improve the approximation of the target distribution. 

Vision Transformer (ViT)-based image super-resolution (SR) methods have achieved impressive performance and surpassed CNN-based SR methods by utilizing Multi-Head Self-Attention (MHSA) to model long-range dependencies. However, the quadratic complexity of MHSA and the inefficiency of non-parallelized window partition seriously affect the inference speed, hindering these SR methods from being applied to application scenarios requiring speed and quality.

Learning-based approaches inspired by the scattering model for enhancing underwater imagery have gained prominence. Nevertheless, these methods often suffer from time-consuming attributable to their sizable model dimensions. Moreover, they face challenges in adapting unknown scenes, primarily because the scattering model's original design was intended for atmospheric rather than marine condition.

Decoding silent reading Electroencephalography (EEG) signals is challenging because of its low signal-to-noise ratio. In addition, EEG signals are typically non-Euclidean structured, therefore merely using a two-dimensional matrix to represent the variation of sampling points of each channel in time cannot richly represent the spatial connection between channels. 

This letter proposes a generalised extended nested array with multiple subarrays (GENAMS) array via the maximum inter-element spacing (IES) constraint principle. Based on the IES set patterns of the two-sides extended nested array and the flexible extended nested array with multiple subarrays type-2, a generalised IES set pattern is derived.

3D face reconstruction from a single image still suffers from low accuracy and inability to recover textures in invisible regions. In this paper, we propose a method for generating a 3D portrait with complete texture. The coarse face-and-head model and texture parameters are obtained using 3D Morphable Model fitting. We design an image-geometric inverse renderer that acquires normal, albedo, and light to jointly reconstruct the facial details.

Iterative hard thresholding (IHT) and hard thresholding pursuit (HTP) are two kinds of classical hard thresholding-based algorithms widely used in compressed sensing. Restricted isometry constant (RIC) of sensing matrix which ensures the convergence of iterative algorithms plays a key role in guaranteeing successful recovery. In the analysis of sufficient condition to ensure recovery performance, the RIC δ3s is generally used in previous literature, while δ2s is rarely addressed. In this letter, we first show that the theoretical optimal step-length is 1 while using sufficient condition in terms of δ2s .

The correlation filter(CF)-based tracker is a classic and effective model in the field of visual tracking. For a long time, most CF-based trackers solved filters using only ridge regression equations with l2 -norm, which can make the trained model noisy and not sparse. As a result, we propose a model of adaptive sparse spatially-regularized correlation filters (AS2RCF). Aiming to suppress the noise mixed in the model, we improve it by introducing an l1 -norm spatial regularization term. 

Image registration is a basic task in computer vision, for its wide potential applications in image stitching, stereo vision, motion estimation, and etc. Most current methods achieve image registration by estimating a global homography matrix between candidate images with point-feature-based matching or direct prediction. However, as real-world 3D scenes have point-variant photograph distances (depth), a unified homography matrix is not sufficient to depict the specific pixel-wise relations between two images.

Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this letter, we propose a novel generation-network-based approach, called symmetric saliency-based encoder-decoder (SSED), to generate adversarial voice examples to speaker identification.