-
公开(公告)号：US11821986B1
公开(公告)日：2023-11-21
申请号：US18336899
申请日：2023-06-16
申请人： Hubei University
发明人： Kansong Chen , Lijun Xu , Yao Xiang , Yan Zhang
IPC分类号： G06F7/02 , G06F18/2134 , G06N3/08 , G06N3/0985 , G06F17/14 , G01S17/66 , G06T7/246 , G01S17/00
CPC分类号： G01S17/66 , G01S17/006 , G06F7/023 , G06F18/21345 , G06N3/08 , G06N3/0985 , G06T7/251 , G06F17/147 , G06T2207/20024 , G06T2207/20056 , G06T2207/20081
摘要： The present invention provides a target tracking method, system, device and storage medium, which includes: Determining a target area based on the current frame of a training sample, extracting and fusing histogram of oriented gradient (HOG), color naming (CN), and color space HSV features of the target area to obtain a target template; Determining a target function according to the target template and a spatial regularization weight factor; Introducing the Sherman-Morrison formula into the alternating direction method of multipliers (ADMM) to accelerate the solution of the target function and obtain the response value; Iterating the target tracking model when the response value meets the preset confidence threshold until training is completed to obtain a trained target tracking model, and tracking the target in the video to be observed by using the trained target tracking model.
-
公开(公告)号：US11755901B2
公开(公告)日：2023-09-12
申请号：US15857438
申请日：2017-12-28
申请人： Intel Corporation
发明人： Michael E. Deisher
IPC分类号： G06F5/01 , G06N3/08 , G06F7/57 , G06F7/544 , G06N3/063 , G06N3/02 , G06N3/044 , G06N3/045 , G06N3/048 , G06F7/02
CPC分类号： G06N3/08 , G06F5/01 , G06F7/5443 , G06F7/57 , G06N3/02 , G06N3/044 , G06N3/045 , G06N3/048 , G06N3/063 , G06F7/023
摘要： An apparatus for applying dynamic quantization of a neural network is described herein. The apparatus includes a scaling unit and a quantizing unit. The scaling unit is to calculate an initial desired scale factors of a plurality of inputs, weights and a bias and apply the input scale factor to a summation node. Also, the scaling unit is to determine a scale factor for a multiplication node based on the desired scale factors of the inputs and select a scale factor for an activation function and an output node. The quantizing unit is to dynamically requantize the neural network by traversing a graph of the neural network.
-
公开(公告)号：US20190249225A1
公开(公告)日：2019-08-15
申请号：US16199028
申请日：2018-11-23
申请人： GENOPLAN KOREA INC.
发明人： Soung Sik KIM , Ji Hyun CHUNG , Min Jin KIM , Jung Min KIM , Byung Kyu KANG
IPC分类号： C12Q1/6806 , C12Q1/6876 , G06F7/02 , C12Q1/6837 , C12Q1/686 , B01L3/00
CPC分类号： C12Q1/6806 , B01J2219/00306 , B01L3/5025 , C12Q1/6837 , C12Q1/686 , C12Q1/6876 , G06F7/023 , G16B25/00 , G16B30/00 , G16C20/10
摘要： Provided is a dispenser mapping apparatus for multi-analysis and an operation method thereof according to an embodiment. The method may include receiving analysis information—the analysis information including information relating to at least one of a plurality of samples, a detection gene for each of the plurality of samples, and a primer corresponding to the detection gene which are subject to analysis—dividing a reaction plate into a plurality of areas and sequentially arranging the plurality of samples and the plurality of primers on the plurality of areas of the reaction plate.
-
公开(公告)号：US20190188268A1
公开(公告)日：2019-06-20
申请号：US16193387
申请日：2018-11-16
申请人： Google LLC
CPC分类号： G06F17/2881 , G06F7/023 , G06F7/10 , G06F17/2735 , G06F17/2818 , G06F17/2827 , G06N3/0445 , G06N3/0454 , G10L15/02 , G10L15/16
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural translation systems with rare word processing. One of the methods is a method training a neural network translation system to track the source in source sentences of unknown words in target sentences, in a source language and a target language, respectively and includes deriving alignment data from a parallel corpus, the alignment data identifying, in each pair of source and target language sentences in the parallel corpus, aligned source and target words; annotating the sentences in the parallel corpus according to the alignment data and a rare word model to generate a training dataset of paired source and target language sentences; and training a neural network translation model on the training dataset.
-
公开(公告)号：US10055582B1
公开(公告)日：2018-08-21
申请号：US15268862
申请日：2016-09-19
CPC分类号： G06F21/552 , G06F7/023 , G06F21/56 , G06F21/562 , G06F21/567 , G06F21/577 , G06F2221/034 , G06N20/00 , H04L63/1416 , H04L63/1433
摘要： An apparatus in one embodiment comprises a security appliance having a processor coupled to a memory. The security appliance is associated with at least one storage device and comprises a ransomware detector configured to generate a detection score for one or more sets of files stored in the storage device. The ransomware detector comprises a file analyzer configured to compare characteristics relating to a current state of the files with information stored in a file history database, and a detection score generator having a weighting module for applying weights to respective comparison results from the file analyzer in generating the detection score for the one or more sets of files. The ransomware detector is further configured to generate an alert if the detection score for the one or more sets of files exceeds a specified threshold. The alert may be transmitted by the security appliance to a network security system.
-
公开(公告)号：US09721096B2
公开(公告)日：2017-08-01
申请号：US15180863
申请日：2016-06-13
CPC分类号： G06F21/562 , G06F7/023 , G06F15/18 , G06F21/56 , G06F21/567 , G06F21/577 , H04L63/1433
摘要： A device may identify a set of features associated with the unknown object. The device may determine, based on inputting the set of features into a threat prediction model associated with a set of security functions, a set of predicted threat scores. The device may determine, based on the set of predicted threat scores, a set of predicted utility values. The device may determine a set of costs corresponding to the set of security functions. The device may determine a set of predicted efficiencies, associated with the set of security functions, based on the set of predicted utility values and the set of costs. The device may identify, based on the set of predicted efficiencies, a particular security function, and may cause the particular security function to be executed on the unknown object. The device may determine whether another security function is to be executed on the unknown object.
-
公开(公告)号：US09367685B2
公开(公告)日：2016-06-14
申请号：US14502661
申请日：2014-09-30
CPC分类号： G06F21/562 , G06F7/023 , G06F15/18 , G06F21/56 , G06F21/567 , G06F21/577 , H04L63/1433
摘要： A device may identify a set of features associated with the unknown object. The device may determine, based on inputting the set of features into a threat prediction model associated with a set of security functions, a set of predicted threat scores. The device may determine, based on the set of predicted threat scores, a set of predicted utility values. The device may determine a set of costs corresponding to the set of security functions. The device may determine a set of predicted efficiencies, associated with the set of security functions, based on the set of predicted utility values and the set of costs. The device may identify, based on the set of predicted efficiencies, a particular security function, and may cause the particular security function to be executed on the unknown object. The device may determine whether another security function is to be executed on the unknown object.
摘要翻译： 设备可以标识与未知对象相关联的一组特征。 设备可以基于将特征集合输入到与一组安全功能相关联的威胁预测模型中来确定一组预测的威胁分数。 设备可以基于预测的威胁分数集合来确定一组预测的效用值。 设备可以确定与该组安全功能相对应的一组成本。 该设备可以基于预测的效用值集合和成本集来确定与一组安全功能相关联的一组预测效率。 设备可以基于预测效率的集合来识别特定的安全功能，并且可以导致在未知对象上执行特定的安全功能。 设备可以确定是否对未知对象执行另一个安全功能。
-
公开(公告)号：US20160092684A1
公开(公告)日：2016-03-31
申请号：US14502661
申请日：2014-09-30
CPC分类号： G06F21/562 , G06F7/023 , G06F15/18 , G06F21/56 , G06F21/567 , G06F21/577 , H04L63/1433
摘要： A device may identify a set of features associated with the unknown object. The device may determine, based on inputting the set of features into a threat prediction model associated with a set of security functions, a set of predicted threat scores. The device may determine, based on the set of predicted threat scores, a set of predicted utility values. The device may determine a set of costs corresponding to the set of security functions. The device may determine a set of predicted efficiencies, associated with the set of security functions, based on the set of predicted utility values and the set of costs. The device may identify, based on the set of predicted efficiencies, a particular security function, and may cause the particular security function to be executed on the unknown object. The device may determine whether another security function is to be executed on the unknown object.
摘要翻译： 设备可以标识与未知对象相关联的一组特征。 设备可以基于将特征集合输入到与一组安全功能相关联的威胁预测模型中来确定一组预测的威胁分数。 设备可以基于预测的威胁分数集合来确定一组预测的效用值。 设备可以确定与该组安全功能相对应的一组成本。 该设备可以基于预测的效用值集合和成本集来确定与一组安全功能相关联的一组预测效率。 设备可以基于预测效率的集合来识别特定的安全功能，并且可以导致在未知对象上执行特定的安全功能。 设备可以确定是否对未知对象执行另一个安全功能。
-
9.发明授权Methods and apparatus for determining whether a media presentation device is in an on state or an off state 有权用于确定媒体呈现设备是处于开启状态还是关闭状态的方法和装置公开(公告)号：US08180712B2
公开(公告)日：2012-05-15
申请号：US12242337
申请日：2008-09-30
申请人： Daniel J. Nelson , Brian Scott Mello , Luc Zio , David James Croy
发明人： Daniel J. Nelson , Brian Scott Mello , Luc Zio , David James Croy
IPC分类号： G06F15/18
CPC分类号： G06N5/048 , G06F7/023 , H04H60/32 , H04H60/58 , H04H2201/90
摘要： Methods and apparatus for determining whether a media presentation device is in an on state or an off state are disclosed. A disclosed example method comprises determining first and second characteristics of a signature associated with a signal representative of media content presented via a media presentation device, evaluating the first and second characteristics to determine first and second fuzzy contribution values representing, respectively, degrees with which the first and second characteristics correspond to the media presentation device being in at least one of an on state or an off state, determining a third fuzzy contribution value based on a number of the first and second contribution values indicating the media presentation device is in one of the on or off states, and combining the first, second and third fuzzy contribution values for use in determining whether the media presentation device is in the on state or the off state.
摘要翻译： 公开了用于确定媒体呈现设备是处于接通状态还是断开状态的方法和装置。 所公开的示例性方法包括确定与代表经由媒体呈现设备呈现的媒体内容的信号相关联的签名的第一和第二特征，评估第一和第二特征以确定第一和第二模糊贡献值，所述第一和第二模糊贡献值分别表示 第一和第二特征对应于处于接通状态或关闭状态中的至少一个的媒体呈现设备，基于指示媒体呈现设备的第一和第二贡献值的数量确定第三模糊贡献值为 打开或关闭状态，并且组合第一，第二和第三模糊贡献值以用于确定媒体呈现设备是处于开启状态还是关闭状态。
-
-
-
-
-
-
-
-
搜索结果
65 条记录 (耗时 0.026 秒)
