ID 原文 译文
18035 协同显著目标检测的目的是在包含两张及以上相关图像的图像组中检测共同显著的物体。 Co-saliency object detection aims to discover common and salient objects in an image group whichcontains two or more relevant images.
18036 该文提出一种利用机器学习的方法对协同显著目标进行检测。 In this paper, a method of using machine learning is proposed to detectco-saliency objects.
18037 首先，基于4个评分指标从图像组中选择部分显著目标易于检测的简单图像，构成简单图像集； Firstly, some simple images are selected to form a simple image set based on four scoringindicators.
18038 接着，基于协同一致性的原则，从简单图像集中提取正负样本，并用深度学习模型提取的高维语义特征表示正负样本； Secondly, positive and negative samples are extracted from the simple images set based on co-coherence characteristics, and high-dimensional semantic features are extracted by the deep learning modelwhich receives RGBD four-channels input.
18039 再者，利用正负样本训练的协同显著分类器对图像中的超像素进行分类，得到协同显著目标区域； Thirdly, the co-saliency classifier is trained by positive and negativesamples, and co-saliency maps are generated by testing all the superpixels in the images by the co-saliencyclassifier.
18040 最后，经过一个平滑融合的操作，得到最终的协同显著图。 Finally, a smooth fusion operation is adopted to generate the final co-saliency map.
18041 在公开数据集上的测试结果表明，所提算法在检测精度和检测效率上优于目前的主流算法，并具有较强的鲁棒性。 Experimentalresults on the public benchmark dataset show that the proposed algorithm is superior to the state-of-the-artmethods in terms of accuracy and efficiency, and it is robust.
18042 机器学习已经广泛应用于恶意代码检测中，并在恶意代码检测产品中发挥重要作用。 Machine learning is widely used in malicious code detection and plays an important role in malicious code detection products.
18043 构建针对恶意代码检测机器学习模型的对抗样本，是发掘恶意代码检测模型缺陷，评估和完善恶意代码检测系统的关键。 Constructing adversarial samples for malicious code detection machine learning modelsis the key to discovering defects in malicious code detection models, evaluating and improving malicious codedetection systems.
18044 该文提出一种基于遗传算法的恶意代码对抗样本生成方法， This paper proposes a method for generating malicious code adversarial samples based ongenetic algorithms.