IEEE SPL Article

Although deep convolutional neural networks (DCNN) show significant improvement for single depth map (SD) super-resolution (SR) over the traditional counterparts, most SDSR DCNNs do not reuse the hierarchical features for depth map SR resulting in blurred high-resolution (HR) depth maps. They always stack convolutional layers to make network deeper and wider.

Two-directional two-dimensional canonical correlation analysis ((2D) 2 CCA) directly seeks linear relationship between different image data sets without reshaping images into vectors. However, it fails in finding the nonlinear correlation. 

Many well-known line spectral estimators may experience significant performance loss with noisy measurements. To address the problem, we propose a deep learning denoising based approach for line spectral estimation. The proposed approach utilizes a residual learning assisted denoising convolutional neural network (DnCNN) trained to recover the unstructured noise component, which is used to denoise the original measurements.

The multiple signal classification (MUSIC) algorithmis computationally expensive in the application to joint two-dimensional (2-D) direction-of-arrival (DOA) and time-of-arrival (TOA) estimation based on uniform circular array (UCA) using orthogonal frequency-division multiplexing (OFDM) signal. This letter proposed an efficient way to compute the 3-D spatial-temporal spectrum.

Two-directional two-dimensional canonical correlation analysis ((2D) 2 CCA) directly seeks linear relationship between different image data sets without reshaping images into vectors. However, it fails in finding the nonlinear correlation.

Many well-known line spectral estimators may experience significant performance loss with noisy measurements. To address the problem, we propose a deep learning denoising based approach for line spectral estimation. The proposed approach utilizes a residual learning assisted denoising convolutional neural network (DnCNN) trained to recover the unstructured noise component, which is used to denoise the original measurements.

Over the last years, several stationarity tests have been proposed. One of these methods uses time-frequency representations and stationarized replicas of the signal (known as surrogates) for testing wide-sense stationarity. In this letter, we propose a procedure to improve the original surrogate test.

In this letter, we propose a heuristic method to address sensor bias estimation to improve track-to-track association accuracy. A novel multi-parameter cost function is derived from rigid transformation function and it is minimized by the covariance matrix adaptation evolution strategies algorithm.

Diacritics restoration is a necessary component in order to develop Arabic text to speech systems. When diacritics are present, the phonetic transcription algorithm can be implemented based on a few rules. Restoring Arabic diacritics based on language model scoring is the dominant approach. A fixed vocabulary is usually used to build the language model used for scoring.

The discrete Mumford-Shah formalism has been introduced for the image denoising problem, allowing to capture both smooth behavior inside an object and sharp transitions on the boundary. In this letter, we propose first to extend this formalism to graphs and to the problem of mixing matrix estimation.