本文介绍了一种较为新颖的优化算法——拔河优化算法(tug of war optimization,TWO)[1]。该算法属于自然启发式、基于群体的元启发式算法。利用体育隐喻,将每个候选解视为参与一系列拔河比赛的团队。这些团队根据它们所代表的解的质量...本文介绍了一种较为新颖的优化算法——拔河优化算法(tug of war optimization,TWO)[1]。该算法属于自然启发式、基于群体的元启发式算法。利用体育隐喻,将每个候选解视为参与一系列拔河比赛的团队。这些团队根据它们所代表的解的质量对彼此施加拉力。竞争的团队根据牛顿力学的运动规律移动到新的位置。与许多其他元启发式方法不同,该算法考虑了相互作用团队的质量。TWO适用于全局优化问题,包括不连续、多峰、非光滑和非凸函数。并在本文中与PSO、SA等其它算法进行了对比验证,实验结果表明TWO具有较高的可靠性与搜索速度。展开更多
在可见光红外跟踪(RGB and Thermal Infrared Tracking,RGB-T)的研究中,为了在常规跟踪算法的基础上实现两个模态的有效融合,基于注意力机制提出了一种基于注意力交互的RGB-T跟踪算法。该算法引入注意力机制对可见光和红外两种模态的图...在可见光红外跟踪(RGB and Thermal Infrared Tracking,RGB-T)的研究中,为了在常规跟踪算法的基础上实现两个模态的有效融合,基于注意力机制提出了一种基于注意力交互的RGB-T跟踪算法。该算法引入注意力机制对可见光和红外两种模态的图像特征进行增强和融合,设计了自特征增强编码器对单一模态的特征进行增强,设计了互特征解码器对两个模态增强后的特征进行交互融合。编码器和解码器均采用两层注意力模块。为了减小算法模型的复杂度,对传统注意力模块进行简化,将全连接层改为1×1卷积。此外,该算法对多个卷积层的特征均进行分层融合,以充分挖掘各层卷积特征中的细节和语义信息。在GTOT,RGBT234和LasHeR三个数据集上进行对比测试。实验结果表明,所提算法性能优异,特别是在RGBT234和LasHeR这两个大规模数据集上取得了最优的跟踪结果,验证了注意力机制在RGB-T跟踪中的有效性。展开更多
The star-forming clumps in star-bursting dwarf galaxies provide valuable insights into understanding the evolution of dwarf galaxies.In this paper,we focus on five star-bursting dwarf galaxies featuring off-centered c...The star-forming clumps in star-bursting dwarf galaxies provide valuable insights into understanding the evolution of dwarf galaxies.In this paper,we focus on five star-bursting dwarf galaxies featuring off-centered clumps in the Mapping Nearby Galaxies at Apache Point Observatory survey.Using the stellar population synthesis software Fitting Analysis using Differential evolution Optimization,we obtain the spatially resolved distribution of the star formation history,which allows us to construct the g-band images of the five galaxies at different ages.These images can help us to probe the evolution of the morphological structures of these galaxies.While images of a stellar population older than 1 Gyr are typically smooth,images of a stellar population younger than 1 Gyr reveal significant clumps,including multiple clumps which appear at different locations and even different ages.To study the evolutionary connections of these five galaxies to other dwarf galaxies before their star-forming clumps appear,we construct the images of the stellar populations older than three age nodes,and define them to be the images of the"host"galaxies.We find that the properties such as the central surface brightness and the effective radii of the hosts of the five galaxies are in between those of dwarf ellipticals(dEs)and dwarf irregulars(dIrrs),with two clearly more similar to dEs and one more similar to dIrrs.Among the five galaxies,8257-3704 is particularly interesting,as it shows a previous starburst event that is not quite visible from its gri image,but only visible from images of the stellar population at a few hundred million years.The star-forming clump associated with this event may have appeared at around 600 Myr ago and disappeared at around 40 Myr ago.展开更多
文摘本文介绍了一种较为新颖的优化算法——拔河优化算法(tug of war optimization,TWO)[1]。该算法属于自然启发式、基于群体的元启发式算法。利用体育隐喻,将每个候选解视为参与一系列拔河比赛的团队。这些团队根据它们所代表的解的质量对彼此施加拉力。竞争的团队根据牛顿力学的运动规律移动到新的位置。与许多其他元启发式方法不同,该算法考虑了相互作用团队的质量。TWO适用于全局优化问题,包括不连续、多峰、非光滑和非凸函数。并在本文中与PSO、SA等其它算法进行了对比验证,实验结果表明TWO具有较高的可靠性与搜索速度。
文摘在可见光红外跟踪(RGB and Thermal Infrared Tracking,RGB-T)的研究中,为了在常规跟踪算法的基础上实现两个模态的有效融合,基于注意力机制提出了一种基于注意力交互的RGB-T跟踪算法。该算法引入注意力机制对可见光和红外两种模态的图像特征进行增强和融合,设计了自特征增强编码器对单一模态的特征进行增强,设计了互特征解码器对两个模态增强后的特征进行交互融合。编码器和解码器均采用两层注意力模块。为了减小算法模型的复杂度,对传统注意力模块进行简化,将全连接层改为1×1卷积。此外,该算法对多个卷积层的特征均进行分层融合,以充分挖掘各层卷积特征中的细节和语义信息。在GTOT,RGBT234和LasHeR三个数据集上进行对比测试。实验结果表明,所提算法性能优异,特别是在RGBT234和LasHeR这两个大规模数据集上取得了最优的跟踪结果,验证了注意力机制在RGB-T跟踪中的有效性。
基金supported by National Key R&D Program of China(Nos.2019YFA0405501 and 2022YFF0503402)the National Natural Science Foundation of China(NSFC,Nos.12233005 and 12041302)+6 种基金support from the Natural Science Foundation of Shanghai(Project Number:22ZR1473000)the Program of Shanghai Academic Research Leader(No.22XD1404200)supports from the CAS Pioneer Hundred Talents ProgramUSTC Research Funds of the Double First-Class Initiativethe NSFC grant 12273037the NSFC grants 12033004,12333003support from the NSFC through grants 12273091 and U2031139。
文摘The star-forming clumps in star-bursting dwarf galaxies provide valuable insights into understanding the evolution of dwarf galaxies.In this paper,we focus on five star-bursting dwarf galaxies featuring off-centered clumps in the Mapping Nearby Galaxies at Apache Point Observatory survey.Using the stellar population synthesis software Fitting Analysis using Differential evolution Optimization,we obtain the spatially resolved distribution of the star formation history,which allows us to construct the g-band images of the five galaxies at different ages.These images can help us to probe the evolution of the morphological structures of these galaxies.While images of a stellar population older than 1 Gyr are typically smooth,images of a stellar population younger than 1 Gyr reveal significant clumps,including multiple clumps which appear at different locations and even different ages.To study the evolutionary connections of these five galaxies to other dwarf galaxies before their star-forming clumps appear,we construct the images of the stellar populations older than three age nodes,and define them to be the images of the"host"galaxies.We find that the properties such as the central surface brightness and the effective radii of the hosts of the five galaxies are in between those of dwarf ellipticals(dEs)and dwarf irregulars(dIrrs),with two clearly more similar to dEs and one more similar to dIrrs.Among the five galaxies,8257-3704 is particularly interesting,as it shows a previous starburst event that is not quite visible from its gri image,but only visible from images of the stellar population at a few hundred million years.The star-forming clump associated with this event may have appeared at around 600 Myr ago and disappeared at around 40 Myr ago.
