ID 原文 译文
56958 与此同时,还能详细具体地解释模型的决策依据,即哪些特征在视频哪几帧的表现对某个个体而言最具辨别性. Concretely, our method can reveal discriminative gait features and frame numbers forspecific subjects.
56959 高清图像(高分辨率图像)前景遮罩提取问题是图像合成、自动前景提取等图像处理领域的热点难题,其本质是前景背景像素对的大规模组合优化问题,目前相关研究成果较少. High-resolution image matting is one of the challenges in image composition and foreground extrac?tion. It is essentially a large-scale combinatorial optimization problem for foreground/background pixel pairs.
56960 本文针对问题维度过高难以直接求解这一问题,设计了基于RGB聚类的多类协同优化策略,以实现决策空间的有效降维; However, little attention has been paid to this issue.
56961 给出协同目标反馈的分组优化策略,通过将协同目标中的最优前景背景像素对作为启发式信息反馈给每个分组,实现大规模组合优化问题的分组协同求解. A multiclass collaborative optimization strategy based onRGB color clustering is proposed to reduce the dimension of this problem, addressing the issues caused by itsultrahigh dimension.
56962 在分组优化策略的基础上,论文提出了基于分组协同的群体竞争优化算法(competitive swarm optimization algorithm based on group collaboration,GC-CSO),为高维优化问题分析提供了借鉴. This paper presents a collaborative feedback grouping strategy to solve this large-scalecombinatorial optimization problem. Based on these two strategies, a competitive swarm optimization algorithmbased on group collaboration (GC-CSO) is proposed.
56963 为了验证所提方法的有效性,本文选用alpha matting基准数据集作为测试数据,通过与群体竞争优化算法、典型带分组策略的大规模优化算法进行对比分析,验证了:(1)基于RGB聚类的协同优化策略可以显著地降低问题维度;(2) GC-CSO算法提高了高清图像前景遮罩的提取精度. Its performance is verified experimentally by using an alphamatting dataset, showing that it can significantly reduce the dimension of the image matting problem and out?perform the existent large-scale optimization algorithms with grouping strategies in the alpha matte comparison
56964 目标搜索问题是现实中一类常见的问题,如灾难现场搜救、战场目标侦察等. Target searching is crucial in real-world scenarios such as search and rescue in disaster sites andbattlefield target reconnaissance.
56965 无人机由于其灵活性、低成本、可搭载各类传感器并以集群形式开展协作等优势,是解决大范围、高风险区域目标搜索问题的理想技术方案,当前发展迅速. Unmanned aerial vehicles (UAVs) are an ideal technical solution for targetsearching in large-scale and high-risk areas because they are agile, low cost, and able to collaborate and carrydifferent sensors.
56966 在战场等复杂现实环境中,由于缺乏基础通信设施及干扰的存在,无人机与地面指挥员、无人机之间难以快速、可靠通信,处于通信拒止状态. In complex scenarios like battlefields, due to the lack of communication infrastructures andthe intensive interference, UAVs often operate in communication denied environments.
56967 因此,无人机难以获得指挥员的实时控制信息,需要其具备自主、智能完成任务的能力并开展协同. As a result, fast andreliable communication channels between UAVs and ground operators are difficult to establish.