ID 原文 译文
38936 选取一个经标准编码的子序列，与一个简化编码的子序列，结合生成描述1，其余子序列生成描述2，不同描述分信道传输。 A standard coded subsequence is selected and combined with a simplified coded subsequence to generate description 1, while the other subsequences generate description 2.
38937 多描述的编码结构可以保证即使只接收到单一描述也能保证视频的重建质量， Different descriptions are transmitted by diverse channels. The multiple description coding structure ensures the reconstructed quality of video even only one description is received.
38938 参数重用的方法利用子序列间的相关性，减少了冗余信息，降低了编码开销。 The parameter reuse strategy makes use of the correlation between subsequences to reduce the redundant information and the coding overhead.
38939 实验结果表明，参数重用的HEVC多描述视频编码针对高清视频编码效果明显，边缘解码质量PSNR值仅略低于中心解码0.7 dB，有效地提高了高清视频编码的容错性能。 The experimental results show that, the proposed MDVC coding method with parameters reuse has obvious effect on high-definition video, the average PSNR of side decoded video is only 0.7 dB lower than that of the central one.
38940 进行简化编码子序列的平均编码时间节省了91.7%，实现了高编码效率、低复杂度的HEVC容错编码。 The coding time of simplified coding subsequences can be saved by 91.7% on average, this method realizes an error resilient HEVC solution with high efficiency and low complexity.
38941 图像标注旨在为图像分配一系列的语义标签描述图像的内容。 Image annotation aims at assigning a set of semantic labels to describe the content of the image.
38942 针对高级语义与低级特征之间的语义鸿沟问题，本文提出了基于偏序结构的图像标注方法。 Aiming at the gap of high-level semantics and low-level features in image annotation, this paper proposed an image annotation methodology based on partial order structure.
38943 首先，利用卷积神经网络VGG-19模型提取图像特征。 At first, VGG-19 structure in convolutional neural network was used to extract image features.
38944 然后，利用提取的图像特征计算训练图像与测试图像的相似性得分，得到测试图像的初始邻近集及邻近标签。 Then, calculated the visual score with extracted image features and obtained the initial neighbor set and adjacent labels.
38945 最后，通过构建的属性偏序结构，获得邻近标签的相关语义，提高标签的丰富度;利用构建的对象偏序结构，得到最终的标注候选集。 Finally, through the attribute partial order structure diagram, the method can get the related semantics of the adjacent labels, and the related semantics were used to construct the object partial order structure(OPOS) diagram in the purpose of obtaining the final semantic neighbor set.