ID 原文 译文
38956 为了解决以上问题，本文提出了一种可见光/热红外RGBT双模态加权相关滤波跟踪算法。 To tackle above problems, in this paper, we propose a weighted DCF(Discriminative Correlation Filter) based RGBT tracker.
38957 该算法首先利用可见光图像和热红外图像联合求解权重图，然后利用权重图引导相关滤波器求解过程，最后根据权重图推断前景目标是否被遮挡。 This tracker derives a weight map from a RGBT image pair and guides correlation filter training with this map. The occlusion state of the foreground target is inferred from the weight map.
38958 该算法在公开数据集RGBT234上的结果表明，本文提出的RGBT双模态加权相关滤波跟踪算法能够有效处理目标局部遮挡和目标畸变等情况，实现复杂场景下鲁棒持续的目标跟踪。 Experimental results on the public RGBT234 dataset demonstrate that our tracker is able to cope well with partial occlusion and shape deformation and achieves robust and persistent tracking in complex scenarios.
38959 为了在图像重建质量和网络参数之间取得较好的平衡，本文提出一种基于渐进式特征增强网络的超分辨率(Super-Resolution，SR)重建算法。 In order to achieve a better balance between image restoration quality and network parameters, this paper proposes a super-resolution(SR) method based on progressive feature enhancement network.
38960 该方法主要包含两个模块:浅层信息增强模块和深层信息增强模块。 The method mainly consists of two modules: shallow information enhancement module and deep information enhancement module.
38961 在浅层信息增强模块中，首先利用单层卷积层提取低分辨率(Low-Resolution，LR)图像的浅层信息，再通过我们设计的多尺度注意力块来实现特征的提取和增强。 In the shallow information enhancement module, firstly, the shallow information of low-resolution(LR) image is extracted by single convolution layer, and then we design the multi-scale attention block to achieve feature extraction and enhancement.
38962 深层信息增强模块先利用残差学习块学习图像的深度信息，然后将得到的深层信息通过设计的多尺度注意力块来获得增强后的深层多尺度信息。 The deep information enhancement module first uses the residual learning block to learn the deep information of the image and then employs the designed multi-scale attention block to obtain the enhanced deep multi-scale information.
38963 最后我们利用跳转连接的方式将首层得到的浅层信息和深层多尺度信息进行像素级相加得到融合特征图，再对其进行上采样操作，得到最终的高分辨率(High-Resolution， HR)图像。 Finally, we use a skip-connection to fuse the shallow information obtained at the first layer and the deep multi-scale information at the pixel level and then up-sample the fusion feature maps to obtain the final high-resolution(SR) image.
38964 实验结果表明，相比于一些主流的深度学习超分辨率方法，本文方法重建得到的图像无论是主观效果还是客观指标，都取得了更好的效果。 The experimental results show that, compared with some mainstream deep learning SR methods, the image reconstructed by the proposed method has achieved better results in both subjective and objective indicators.
38965 细粒度图像分类的目标是区分同一个常见类下的不同子类，由于数据集往往存在较大的类内差异和较大的类间相似性，细粒度图像分类相比于传统图像分类具有更大的挑战性。 Fine-grained image classification task focuses on discriminating diffierent sub-classes under the common category. Because of the exiting larger intra-class variance and larger inter-class similarity, fine-grained image classification task is extremely challenging compare with traditional task.