SiamPRN algorithm performs well in visual tracking, but it is easy to drift under occlusion and fast motion scenes because it uses $$\ell _1$$ℓ 1 -smooth loss function to measure the regression location of bounding box. In this paper, we propose a multivariate intersection over union (MIOU) loss in SiamRPN tracking framework. Firstly, MIOU loss includes three geometric factors in regression: the overlap area ratio, the center distance ratio, and the aspect ratio, which can better reflect the coincidence degree of target box and prediction box. Secondly, we improve the definition of aspect ratio loss to avoid gradient explosion, improve the optimization performance of prediction box. Finally, based on SiamPRN tracker, we compared the tracking performance of $$\ell _1$$ℓ 1 -smooth loss, IOU loss, GIOU loss, DIOU loss, and MIOU loss. Experimental results show that the MIOU loss has better target location regression than other loss functions on the OTB2015 and VOT2016 benchmark, especially for the challenges of occlusion, illumination change and fast motion.

Compared with the traditional method based on hand-crafted features, deep neural network has achieved a certain degree of success on remote sensing image semantic segmentation. However, there are still serious holes, rough edge segmentation, and false detection or even missed detection due to the light and its shadow in the segmentation. Aiming at the above problems, this paper proposes a remote sensing semantic segmentation model SCG-TransNet that is a hybrid model of Swin Transformer and Deeplabv3+, which includes Swin-Conv-Dspp (SCD) and Global Local Transformer Block (GLTB). First, SCD module which can efficiently extract feature information from objects at different scales is used to mitigate the hole phenomenon, reducing the loss of detailed information. Second, we construct a GLTB with Spatial Pyramid Pooling Shuffle(SPPS) module to extract critical detail information from the limited visible pixels of the occluded objects, which alleviates the problem of difficult object recognition due to occlusion effectively. Finally, the experimental results show that our SCG-TransNet achieves a Mean Intersection over Union (MIoU) of 70.29 $\%$ on the Vaihingen datasets, which is 3 $\%$ higher than the baseline model. It also achieved good results on Potsdam datasets. These demonstrate the effectiveness, robustness and superiority of our proposed method compared with existing state-of-the-art methods. The code will be available at https://github.com/yuwxyun275/SCG-TransNet .

This paper is concerned with mobile coded orthogonal frequency division multiplexing (OFDM) systems. In the high-speed railway wireless communication system, an equalizer or detector should be used to mitigate the intercarrier interference (ICI) and deliver the soft message to the decoder with the soft demapper. In this paper, a Transformer-based detector/demapper is proposed to improve the error performance of the mobile coded OFDM system. The soft modulated symbol probabilities are computed by the Transformer network, and are then used to calculate the mutual information to allocate the code rate. Then, the network computes the codeword soft bit probabilities, which are delivered to the classical belief propagation (BP) decoder. For comparison, a deep neural network (DNN)-based system is also presented. Numerical results show that the Transformer-based coded OFDM system outperforms both the DNN-based and the conventional system.