-
公开(公告)号：US20130132316A1
公开(公告)日：2013-05-23
申请号：US13491108
申请日：2012-06-07
申请人： Jinjun Wang , Zhaowen Wang , Jing Xiao
发明人： Jinjun Wang , Zhaowen Wang , Jing Xiao
IPC分类号： G06N5/02
CPC分类号： G06N99/005
摘要： Embodiments of the present invention include systems and methods for improved state space modeling (SSM) comprising two added layers to model the substructure transition dynamics and action duration distribution. In embodiments, the first layer represents a substructure transition model that encodes the sparse and global temporal transition probability. In embodiments, the second layer models the action boundary characteristics by injecting discriminative information into a logistic duration model such that transition boundaries between successive actions can be located more accurately; thus, the second layer exploits discriminative information to discover action boundaries adaptively.
摘要翻译： 本发明的实施例包括用于改进状态空间建模（SSM）的系统和方法，所述状态空间建模（SSM）包括两个附加的层，以模拟子结构转变动力学和动作持续时间分布。 在实施例中，第一层表示编码稀疏和全局时间转移概率的子结构转换模型。 在实施例中，第二层通过将识别信息注入逻辑持续时间模型来建模动作边界特征，使得可以更准确地定位连续动作之间的转移边界; 因此，第二层利用辨别信息自动发现行动界限。
-
公开(公告)号：US08892491B2
公开(公告)日：2014-11-18
申请号：US13491108
申请日：2012-06-07
申请人： Jinjun Wang , Zhaowen Wang , Jing Xiao
发明人： Jinjun Wang , Zhaowen Wang , Jing Xiao
CPC分类号： G06N99/005
摘要： Embodiments of the present invention include systems and methods for improved state space modeling (SSM) comprising two added layers to model the substructure transition dynamics and action duration distribution. In embodiments, the first layer represents a substructure transition model that encodes the sparse and global temporal transition probability. In embodiments, the second layer models the action boundary characteristics by injecting discriminative information into a logistic duration model such that transition boundaries between successive actions can be located more accurately; thus, the second layer exploits discriminative information to discover action boundaries adaptively.
摘要翻译： 本发明的实施例包括用于改进状态空间建模（SSM）的系统和方法，所述状态空间建模（SSM）包括两个附加层以对子结构转变动力学和动作持续时间分布进行建模。 在实施例中，第一层表示编码稀疏和全局时间转移概率的子结构转换模型。 在实施例中，第二层通过将识别信息注入逻辑持续时间模型来建模动作边界特征，使得可以更准确地定位连续动作之间的转移边界; 因此，第二层利用辨别信息自动发现行动界限。
-
公开(公告)号：US20230246649A1
公开(公告)日：2023-08-03
申请号：US18103448
申请日：2023-01-30
申请人： Zhaowen Wang , Peter Kinget
发明人： Zhaowen Wang , Peter Kinget
CPC分类号： H03L7/0998 , H03L7/0818
摘要： Phase interpolators are provided, the phase interpolators including: a first phase interpolator having a first output that outputs a first interpolated clock signal based on quadrature clock signals and a first phase interpolator control signal; a second phase interpolator having a second output that outputs a second interpolated clock signal based on the quadrature clock signals and a second phase interpolator control signal that is shifted from the first phase interpolator control signal by half of an integral nonlinearity (INL) period of the first phase interpolator; and a phase combiner that outputs a third interpolated clock signal based on the first interpolated clock signal and the second interpolated clock signal. In some of these embodiments, the phase interpolators further comprise a first amplitude limiter that receives the first interpolated clock signal and outputs a first amplitude-limited interpolated clock signal that is provided to the phase combiner.
-
-
搜索结果
3 条记录 (耗时 0.019 秒)
