| ID | 原文 | 译文 |
| 16435 | 其次，基于图卷积中可处理变长邻居节点的图卷积核，引入3维卷积的3维采样空间将2维图卷积核改进为具有3维采样空间的3维图卷积核，提出一种3维图卷积方法。 | Secondly, a3D graph convolution method is proposed. It is based on the graph convolution kernel that can handle variable-length neighbor nodes in graph and 3D sampling space of 3D convolution is introduced to improve 2D graphconvolution kernel to 3D graph convolution kernel with 3D sampling space. |
| 16436 | 针对3维采样空间内的邻居节点，通过3维图卷积核，实现了对骨架序列中时空信息的有效提取； | For neighbor nodes in 3D sampling space, this method realizes effective extraction of spatial-temporal information with a 3D graph convolution kernel; |
| 16437 | 然后，为增强对于特定关节的关注，聚焦重要的动作信息，设计了一种注意力增强结构； | Thirdly, in order to enhance attention to specific joints and focus important action information, anattention enhanced structure is designed. |
| 16438 | 再者，结合3维图卷积方法与注意力增强结构，构建了基于3维图卷积与注意力增强的行为识别模型； | Besides, through combining 3D graph convolution with attentionenhanced structure, action recognition model based on 3D graph convolution and attention enhanced isproposed. |
| 16439 | 最后，基于NTU-RGBD和MSR Action 3D骨架动作数据集开展了骨架行为识别的研究。 | Finally, the researches are carried on NTU-RGBD and MSR Action 3D skeleton action dataset. |
| 16440 | 研究结果进一步验证了基于3维图卷积与注意力增强的行为识别模型针对时空信息的有效提取能力及识别准确率。 | The results further verify the ability to extract spatial-temporal information of this model and its classificationaccuracy. |
| 16441 | 像素间的上下文相关信息对图像分割算法的抗噪性和准确性具有重要意义，现有的模糊C均值(FCM)聚类算法对此缺乏充分考虑。 | The correlation information between pixels is of great significance for image segmentation. The existing Fuzzy C-Means (FCM) clustering algorithm lacks sufficient consideration for it. |
| 16442 | 该文基于对空间上下文的可靠性度量，提出一种模糊C均值聚类算法(RSFCM)应用于图像分割：通过对空间上下文有效建模来提高聚类算法的抗噪声干扰性能，并研究了一种新的可靠性模糊度量指标，使聚类算法能更好地平衡细节保留和去噪，从而获得更加准确的分割结果。 | Based on the reliabilitymeasure of spatial context, this paper proposes a Reliability-based Spatial context Fuzzy C-Means (RSFCM)clustering algorithm: The clustering algorithm anti-noise performance is improved by effectively modeling thespatial neighborhood; A new reliability fuzzy metric is proposed, which balances the relationship between detailretention and anti-noise, so that the clustering results are more accurate. |
| 16443 | 实验选取人工合成图像、交通标志图像和遥感图像3类数据测试聚类算法性能，结果表明，RSFCM在图像分割过程中能有效地抑制椒盐噪声和高斯噪声引起的类内异构及类间同构问题，能提高图像的像素可分性，并有效地保留了图像的边缘细节。 | A synthetic image, a traffic sign imageand a remote sensing image are used to test the algorithms performance. The results show, compared with theexisting FCM algorithm, RSFCM can effectively suppress heterogeneity of intra-class objects caused by Salt &Pepper noise and Gaussian noise for the image segmentation, improve pixels separability and preserve the edgedetails of the image greatly. |
| 16444 | 针对当前目标检测算法对小目标及密集目标检测效果差的问题，该文在融合多种特征和增强浅层特征表征能力的基础上提出了浅层特征增强网络(SEFN)， | Current object detection algorithms have poor detection results on small targets and dense targets.To address this challenge, a Shallow Enhanced Feature Network (SEFN) is proposed in this paper, which isbased on the fusion of multiple features and enhanced shallow feature characterization capabilities. |