Image stitching aims at generating high-quality panoramas with the lowest computational cost. In this paper, we propose a parallax-tolerant image stitching method based on robust elastic warping, which could achieve accurate alignment and efficient processing simultaneously. Given a group of point matches between images, an analytical warping function is constructed to eliminate the parallax errors. Then the input images are warped according to the computed deformations over the meshed image plane. The seamless panorama is composed by directly re-projecting the warped images. As an important complement to the proposed method, a Bayesian model of feature refinement is proposed to adaptively remove the incorrect local matches. This ensures a more robust alignment than existing approaches. Moreover, our warp is highly compatible with different transformation types. A flexible strategy of combining it with the global similarity transformation is provided as an example. The performance of the proposed approach is demonstrated using several challenging cases.

Conventional deep neural networks based video object segmentation (VOS) methods are dominated by heavily fine-tuning a segmentation model on the first frame of a given video, which is time-consuming and inefficient. In this paper, we propose a novel method which rapidly adapts a base segmentation model to new video sequences with only a couple of model-update iterations, without sacrificing performance. Such attractive efficiency benefits from the meta-learning paradigm which leads to a meta-segmentation model and a novel continuous learning approach which enables online adaptation of the segmentation model. Concretely, we train a meta-learner on multiple VOS tasks such that the meta model can capture their common knowledge and gains the ability to fast adapt the segmentation model to new video sequences. Furthermore, to deal with unique challenges of VOS tasks from temporal variations in the video, e.g., object motion and appearance changes, we propose a principled online adaptation approach that continuously adapts the segmentation model across video frames by exploiting temporal context effectively, providing robustness to annoying temporal variations. Integrating the meta-learner with the online adaptation approach, the proposed VOS model achieves competitive performance against the state-of-the-arts and moreover provides faster per-frame processing speed.

Cross-scene hyperspectral image (HSI) classification has received widespread attention due to its practicality. However, domain adaptation (DA)-based cross-scene HSI classification methods are typically tailored for a specific target scene involved in model training and require retraining for new scenes. We instead propose a novel spectral–spatial adversarial multidomain synthetic network (S2AMSnet) that can be trained on a single source domain (SD) and generalized to unseen domains. S2AMSnet improves the robustness of the model to the unseen domain by expanding the diverse distribution of the SD. Specifically, to spatially and spectrally generate diversified generative domain (GD), the spectral–spatial domain-generation network (S2DGN) is designed, and two S2DGNs with the same structure but not shared parameters are enabled to generate diversified GD through two-step min–max strategy. A Multidomain mixing module is employed to expand the diversity of the GD further and enhance their class-domain semantic consistency information. In addition, a multiscale mutual information (MI) regularization network (MMIRN) is used to constrain the S2DGN so that the intrinsic class semantic information of its generated GD does not deviate from the SD. A semantic consistency discriminator with spectral–spatial feature extraction capability is utilized to capture class-domain semantic consistency information from diverse GD to obtain cross-domain invariant knowledge. Comparative analysis with eight state-of-the-art transfer learning methods on three real HSI datasets, along with an ablation study, validates the effectiveness of the proposed S2AMSnet in the cross-scene HSI classification task. The codes of this work will be available at https://github.com/daxichen/S2AMSnet .

In this letter, we present an efficient image denoising method combining quadtree-based nonlocal means (NLM) and locally adaptive principal component analysis. It exploits nonlocal multiscale self-similarity better, by creating sub-patches of different sizes using quadtree decomposition on each patch. To achieve spatially uniform denoising, we propose a local noise variance estimator combined with denoiser based on locally adaptive principal component analysis. Experimental results demonstrate that our proposed method achieves very competitive denoising performance compared with state-of-the-art denoising methods, even obtaining better visual perception at high noise levels.

Mathematical programming is a rich and well-developed area in operations research. Nevertheless, there remain many challenging problems in this area, one of which is the large-scale optimization problem. In this article, a modified Hestenes and Stiefel (HS) conjugate gradient (CG) algorithm with a nonmonotone line search technique is presented. This algorithm possesses information about not only the gradient value but also the function value. Moreover, the sufficient descent condition holds without any line search. The global convergence is established for nonconvex functions under suitable conditions. Numerical results show that the proposed algorithm is advantageous to existing CG methods for large-scale optimization problems.

With the recent climate changes, investors and policy-makers are paying close attention to the green bond market. This study intends to analyze the dynamic effects of shock transmission between climate policy uncertainty and the green bond market and to offer some new perspectives on analysis of green bond volatility over the previous years. To investigate time-varying effects of climate policy uncertainty on green bond market volatility, we applied a TVP-VAR model. And the impact of three important time points is tested, which are the Paris Association convening in December 2015, the 2017 annual Report on Policies and Actions of China on Climate Change in October 2017 and the “double carbon” policy in September 2020. The finding is that: (1) This impact of climate policy uncertainty on the volatility of the green bond market is time-varying, with short-term overreactions or underreactions as well as medium and long-term inversions. (2) This impact is also time-varying at different time points and has a certain degree of sustainability.