Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,rese...Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains scarce.Given the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed macaques.Our approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label classification.We also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their cages.The dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the macaques.Experimental results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation networks.In conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.展开更多
Many problems in engineering shape design involve eigenvalue optimizations.The relevant difficulty is that the eigenvalues are not continuously differentiable with respect to the density.In this paper,we are intereste...Many problems in engineering shape design involve eigenvalue optimizations.The relevant difficulty is that the eigenvalues are not continuously differentiable with respect to the density.In this paper,we are interested in the case of multi-density inhomogeneous materials which minimizes the least eigenvalue.With the finite element discretization,we propose a monotonically decreasing algorithm to solve the minimization problem.Some numerical examples are provided to illustrate the efficiency of the present algorithm as well as to demonstrate its availability for the case of more than two densities.As the computations are sensitive to the choice of the discretization mesh sizes,we adopt the refined mesh strategy,whose mesh grids are 25-times of the amount used in[S.Osher and F.Santosa,J.Comput.Phys.,171(2001),pp.272-288].We also show the significant reduction in computational cost with the fast convergence of this algorithm.展开更多
基金supported by the Major Project of the National Natural Science Foundation of China (82090051,81871442)Outstanding Member Project of Youth Innovation Promotion Association of the Chinese Academy of Sciences (Y201930)。
文摘Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains scarce.Given the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed macaques.Our approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label classification.We also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their cages.The dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the macaques.Experimental results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation networks.In conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.
基金supported by the Chinese National Science Foundation(No.10871179)the National Basic Research Programme of China(No.2008CB717806)Specialized Research Fund for the Doctoral Program of Higher Education of China(SRFDP No.20070335201).
文摘Many problems in engineering shape design involve eigenvalue optimizations.The relevant difficulty is that the eigenvalues are not continuously differentiable with respect to the density.In this paper,we are interested in the case of multi-density inhomogeneous materials which minimizes the least eigenvalue.With the finite element discretization,we propose a monotonically decreasing algorithm to solve the minimization problem.Some numerical examples are provided to illustrate the efficiency of the present algorithm as well as to demonstrate its availability for the case of more than two densities.As the computations are sensitive to the choice of the discretization mesh sizes,we adopt the refined mesh strategy,whose mesh grids are 25-times of the amount used in[S.Osher and F.Santosa,J.Comput.Phys.,171(2001),pp.272-288].We also show the significant reduction in computational cost with the fast convergence of this algorithm.
