ID 原文 译文
16425 由此，该文提出了两种多项式时间的精确算法：信任关系约束下的MT-s-t-cut算法和信任效用关系约束下的MTU-s-t-cut算法，这两种算法均能够在多项式时间内得到最优联盟结构。 The proposed algorithms of coalition structure generation named MT-s-t-cut and MTU-s-t-cut (Trust s-t-cut) can output the optimal coalition structure in polynomial time.
16426 仿真实验验证了信任关系影响所形成的联盟结构，社会整体效用随智能体数量的增加而增加，并且算法的运行时间远小于动态规划法(DP)和ODP-IP算法。 The results of simulated experiments show that the social utilityincreases with the number of agents, and the running time of the algorithms are far less than that of DynamicProgramming (DP) and Optimal Dynamic Programming and Integer Partition (ODP-IP) algorithms.
16427 作为计算机视觉和图像处理研究领域中的经典课题，行人检测技术在智能驾驶、视频监控等领域中具有广泛的应用空间。 As a classic subject in computer vision and image processing, pedestrian detection has a wide range ofapplications to intelligence driving and video monitoring fields.
16428 然而，面对一些复杂的环境和情况，如阴雨、雾霾、被遮挡、照明度变化、目标尺度差异大等，常见的基于可见光或红外图像的行人检测方法的效果尚不尽如人意，无论是在检测准确率还是检测速度上。 However, most of pedestrian detection methodsbased on visible or infrared images have no satisfying result in some complex environments or situations, suchas rain, smog, occlusion, variation of illuminance and target scales, no matter in terms of detection accuracy orspeed.
16429 该文分析并抓住可见光和红外检测系统中行人特征差异较大，但在不同环境中又各有优势的特点， This paper analyzes and finds out that, pedestrians usually have quite different characteristics in visibleand infrared image, and which have their own advantages in different environments.
16430 并结合多尺度特征提取方法，提出一种适用于多样复杂环境下多尺度行人实时检测的方法——融合行人检测网络(FPDNet)。 Therefore, combining fusion and multi-scale technology, a real-time multi-scale pedestrian detection algorithm suitable for complex environment named FPDNet (Fusion Pedestrian Detection Network) is proposed.
16431 该网络主要由特征提取骨干网络、多尺度检测和信息决策融合3个部分构成，可自适应提取可见光或红外背景下的多尺度行人。 The detection framework is consisted by three main modules: feature extraction backbone network, multi-scale detection network and decision-level fusion network. The proposed method is able to extract multi-scale pedestrian characteristicsunder visible or infrared background adaptively.
16432 实验结果证明，该检测网络在多种复杂视觉环境下都具有较好的适应能力，在检测准确性和检测速度上均能满足实际应用的需求。 Experimental results prove that the detection network hasgood adaptability in complex visual environments, and can meet the demands of practical applications todetection accuracy and speed.
16433 针对当前行为识别方法无法有效提取非欧式3维骨架序列的时空信息与缺乏针对特定关节关注的问题，该文提出了一种基于3维图卷积与注意力增强的行为识别模型。 To solve the problems that current behavior recognition methods can not effectively extract thespatial-temporal information in non-European 3D skeleton sequence and lack attention for specific joints, anaction recognition model based on 3D graph convolution and attention enhanced is proposed in this paper.
16434 首先，介绍了3维卷积与图卷积的具体工作原理； Firstly, the specific working principles of the 3D convolution and graph convolution are introduced;