Different from object detection in natural image, optical remote sensing object detection is a challenging task, due to the diverse meteorological conditions, complex background, varied orientations, scale variations, etc. In this paper, to address this issue, we propose a novel object detection network (the global-local saliency constraint network, GLS-Net) that can make full use of the global semantic information and achieve more accurate oriented bounding boxes. More precisely, to improve the quality of the region proposals and bounding boxes, we first propose a saliency pyramid which combines a saliency algorithm with a feature pyramid network, to reduce the impact of complex background. Based on the saliency pyramid, we then propose a global attention module branch to enhance the semantic connection between the target and the global scenario. A fast feature fusion strategy is also used to combine the local object information based on the saliency pyramid with the global semantic information optimized by the attention mechanism. Finally, we use an angle-sensitive intersection over union (IoU) method to obtain a more accurate five-parameter representation of the oriented bounding boxes. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed GLS-Net achieves a state-of-the-art detection performance.

Although many state-of-the-art object detectors have been developed, detecting small and densely packed objects with complicated orientations in remote sensing aerial images remains challenging. For object detection in remote sensing aerial images, different scales, sizes, appearances, and orientations of objects from different categories could most likely enlarge the variance in the detection error. Undoubtedly, the variance in the detection error should have a non-negligible impact on the detection performance. Motivated by the above consideration, in this paper, we tackled this issue, so that we could improve the detection performance and reduce the impact of this variance on the detection performance as much as possible. By proposing a scaled smooth L${}_1$ loss function, we developed a new two-stage object detector for remote sensing aerial images, named Faster R-CNN-NeXt with RoI-Transformer. The proposed scaled smooth L${}_1$ loss function is used for bounding box regression and makes regression invariant to scale. This property ensures that the bounding box regression is more reliable in detecting small and densely packed objects with complicated orientations and backgrounds, leading to improved detection performance. To learn rotated bounding boxes and produce more accurate object locations, a RoI-Transformer module is employed. This is necessary because horizontal bounding boxes are inadequate for aerial image detection. The ResNeXt backbone is also adopted for the proposed object detector. Experimental results on two popular datasets, DOTA and HRSC2016, show that the variance in the detection error significantly affects detection performance. The proposed object detector is effective and robust, with the optimal scale factor for the scaled smooth L${}_1$ loss function being around 2.0. Compared to other promising two-stage oriented methods, our method achieves a mAP of 70.82 on DOTA, with an improvement of at least 1.26 and up to 16.49. On HRSC2016, our method achieves an mAP of 87.1, with an improvement of at least 0.9 and up to 1.4.

Capital allocation is of fundamental importance in risk management. Capital allocation problems with univariate risk measures have been extensively studied in the finance literature. In contrast, the studies about capital allocations with multivariate risk measures are quite insufficient in the literature. In this paper, we study capital allocations with multivariate coherent and convex risk measures. First, we propose the definitions of capital allocation problem and principle for general multivariate risk measures. Then based on the dual representations proved by [41], we provide the capital allocation principles with multivariate coherent and convex risk measures. Their properties are also investigated. For the case of multivariate convex risk measures, we also suggest a reasonable and effective capital allocation scheme. Finally, examples are given to illustrate the effectiveness of the proposed capital allocation scheme, where the involved convex risk measures are multivariate and univariate entropic risk measures, respectively.

In this paper, by proposing a new risk measure called CoRVaR, we explore the risk spillover effect within a financial system consisting of the banking, security and insurance industries. To be precise, we examine the risk spillover effect from each industry to the other. Moreover, we also examine the risk spillover effect from each industry to the system. The dependence structure between industries is modeled using the vine copula. By employing the Monte Carlo simulation technique, an empirical study via data from Chinese financial markets is implemented. Finally, backtesting and comparisons with existing results are also performed. It turns out that the proposed risk measure can well quantify the risk spillover effect. In addition, the copula employed can also well reveal the interdependence structure of the financial system.

In this paper, we investigate multi-period multivariate risk measures as well as multivariate risk statistics. To be precise, by proposing new sets of axioms, we introduce two new classes of multi-period coherent and convex multivariate risk measures first, and then we provide dual representations for them. Equivalent conditions for dual representation are also given. Time consistency is also discussed. Moreover, we axiomatically introduce multi-period coherent and convex multivariate risk statistics. Dual representations for these multi-period multivariate risk statistics are derived. This paper provides some relevant theoretical results about the evaluation of multivariate risks in the multi-period setting, and provides a non-trivial generalization of several known achievements in the literature.

In this paper, we aim to discuss an axiom system for capital allocation with multivariate risk statistics. First, we introduce a class of multivariate risk statistics satisfying the properties of positive homogeneity and subadditivity, and provide the representations. Second, the axiom system of capital allocation with multivariate risk statistics are discussed. Specifically, the existence and the uniqueness of the capital allocation principles with positively homogeneous and subadditive risk statistics are studied. Finally, examples are also given to illustrate the proposed axioms for capital allocation with multivariate risk statistics, where the explicit capital allocation principles are derived for two kinds of multivariate risk statistics based on mean and standard deviation. The proposed capital allocations with multivariate risk statistics directly base on the samples of the random vectors, and thus they are more tractable than those with multivariate risk measures.