International Journal of Wavelets, Multiresolution and Information Processing

3D image reconstruction using multi-view imaging is widely utilized in several application domains: construction field, disaster management, urban planning, etc. The 3D reconstruction from the multi-view image is still challenging due to the high freedom and inaccurate reconstruction. This research introduces the hybrid deep learning technique for reconstructing the 3D image, in which the C-dual attention layer is proposed for generating the feature map to support the image reconstruction. The proposed 3D image reconstruction uses the encoder–decoder–refiner which is utilized for reconstruction. Initially, the features are extracted from the AlexNet and ResNet-50 features automatically. Then, the proposed C-dual attention layer is utilized for generating the inter-channel and inter-spatial relationship among the features to obtain enhanced reconstruction accuracy. The inter-channel relationship is evaluated using the channel attention layer, and the inter-spatial relationship is evaluated using the spatial attention layer of the encoder module. Here, the features generated by the spatial attention layer are combined to form the feature map in a 2D map. The proposed C-dual attention encoder provides enhanced features that help to acquire enhanced 3D image reconstruction. The proposed method is evaluated based on loss, IoU_3D, and IoU_2D, and acquired the values of 0.0721, 1.25 and 1.37, respectively.

Hyperspectral image (HSI) classification has long been a hot research topic. Most previous researches concentrate on the classification task of a single HSI scene, called single-scene classification. This research focuses on two closely related HSI scenes (called source and target scenes, respectively), and the problem is named cross-scene classification. This paper aims to explore the shared feature sub-space between two HSI scenes. A transfer learning algorithm called cross-domain residual deep nonnegative matrix factorization (CDRDNMF) is proposed. CDRDNMF is a multi-layer architecture consisting of dual-dictionary nonnegative matrix factorization (DDNMF) layers. In each layer, DDNMF is performed on source and target features for domain-invariant feature extraction. Then a data recovery process is completed, and the residual components from the recovery are passed to the next layer after activation. With such a multi-layer architecture, CDRDNMF delivers knowledge transfer and multi-scale feature extraction tasks. The experimental results prove the excellent performance of CDRDNMF on cross-scene classification.

We propose the Rescaled Pure Greedy Learning Algorithm (RPGLA) for solving the kernel-based regression problem. The computational complexity of the RPGLA is less than the Orthogonal Greedy Learning Algorithm (OGLA) and Relaxed Greedy Learning Algorithm (RGLA). We obtain the convergence rates of the RPGLA for continuous kernels. When the kernel is infinitely smooth, we derive a convergence rate that can be arbitrarily close to the best rate $O(m^{-1})$ under a mild assumption of the regression function.

Digital forgery is increasing day by day due to the increase in the usage of digital media files and the ease of editing media files. But digital media editing is a serious issue, as digital media are the primary source of evidence for criminal cases in the courtrooms. Consequently, there is an urge to detect and localize forgeries in digital media to aid digital forensics. The main aim of the proposed work is to detect forgeries in digital images. Image splicing forgery involves copying an image region from one image and pasting it into another image. A deep learning-based technique is proposed to detect image splicing forgery. A pre-trained deep Convolution Neural Network is transferred for the proposed application. The network is trained using spliced and original images to adapt it to the image splicing detection problem. The layers in the network are modified and fine-tuned to make it perform well for the new unseen dataset. This re-designed convolution network discriminates spliced and original images accurately. Also, the proposed work locates the spliced image regions if both the source and spliced images are provided as input image pairs. The proposed work is tested on CASIA and Columbia splicing image datasets and achieved good results.

In this paper, mainly the exact traveling waves fitting the mathematical model in electro-cardio-physiology have been investigated. The source functions of noise-type are used in the proposed coupled system of nonlinear partial differential equations. The Ricatti–Bernoulli Sub-ODE method together with the Bäcklund extension is applied. The interesting plots for the obtained traveling waves and solitons are shown. The proposed model provides new applications for the considerations under the electric pulses or shocks. The application of current method and the modification of classical existence theory are first time applied to the stochastic nonlinear problems in electro-cardiac-physiology.

Zero-shot sketch-based image retrieval (ZSSBIR) aims at retrieving natural images given free hand-drawn sketches that may not appear during training. Previous approaches used semantic aligned sketch-image pairs or utilized memory expensive fusion layer for projecting the visual information to a low-dimensional subspace, which ignores the significant heterogeneous cross-domain discrepancy between highly abstract sketch and relevant image. This may yield poor performance in the training phase. To tackle this issue and overcome this drawback, we propose a Wasserstein distance-based cross-modal semantic network (WAD-CMSN) for ZSSBIR. Specifically, it first projects the visual information of each branch (sketch, image) to a common low-dimensional semantic subspace via Wasserstein distance in an adversarial training manner. Furthermore, a novel identity matching loss is employed to select useful features, which can not only capture complete semantic knowledge, but also alleviate the over-fitting phenomenon caused by the WAD-CMSN model. Experimental results on the challenging Sketchy (Extended) and TU-Berlin (Extended) datasets indicate the effectiveness of the proposed WAD-CMSN model over several competitors.

Due to the demand for tackling the problem of streaming data with high-dimensional covarites, we propose an online sparse sliced inverse regression (OSSIR) method for online sufficient dimension reduction (SDR). The existing online SDR methods focus on the case when $p$ (dimension of covariates) is small. In this paper, we adapt the sparse sliced inverse regression to cope with high-dimensional streaming data where the dimension $p$ is large. There are two important steps in our method, one is to extend the online principal component analysis to iteratively obtain the eigenvalues and eigenvectors of the kernel matrix, the other is to use the truncated gradient to perform online $L_1$ regularization. Theoretical properties of the proposed online learner are established. By comparing with several existing methods in simulations and real data applications, we demonstrate the effectiveness and efficiency of our method.

The presence of spikes or cusps in high-frequency return series might generate problems in terms of inference and estimation of the parameters in volatility models. For example, the presence of jumps in a time series can influence sample autocorrelations, which can cause misidentification or generate spurious ARCH effects. On the other hand, these jumps might also hide relevant heteroskedastic behavior of the dependence structure of a series, leading to identification issues and a poorer fit to a model. This paper proposes a wavelet-shrinkage method to separate out jumps in high-frequency financial series, fitting a suitable model that accounts for its stylized facts. We also perform simulation studies to assess the effectiveness of the proposed method, in addition to illustrating the effect of the jumps in time series. Lastly, we use the methodology to model real high-frequency time series of stocks traded on the Brazilian Stock Exchange and OTC and a series of cryptocurrencies trades.