中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.014 seconds)

    MULTI-CAMERA ENTITY TRACKING TRANSFORMER MODEL
    1.
    发明申请
    MULTI-CAMERA ENTITY TRACKING TRANSFORMER MODEL 有权

    公开(公告)号：US20250148624A1

    公开(公告)日：2025-05-08

    申请号：US18934512

    申请日：2024-11-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Deep Patel ,  Iain Melvin ,  Alexandru Niculescu-Mizil

    IPC: G06T7/292 ,  G06T7/00 ,  G06T7/70

    Abstract: Systems and methods for a multi-entity tracking transformer model (MCTR). To train the MCTR, processing track embeddings and detection embeddings of video feeds obtained from multiple cameras to generate updated track embeddings with a tracking module. The updated track embeddings can be associated with the detection embeddings to generate track-detection associations (TDA) for each camera view and camera frame with an association module. A cost module can calculate a differentiable loss from the TDA by combining a detection loss, a track loss and an auxiliary track loss. A model trainer can train the MCTR using the differentiable loss and contiguous video segments sampled from a training dataset to track multiple objects with multiple cameras.

    SYMBOLIC KNOWLEDGE IN DEEP MACHINE LEARNING
    2.
    发明申请
    SYMBOLIC KNOWLEDGE IN DEEP MACHINE LEARNING 有权

    公开(公告)号：US20240378440A1

    公开(公告)日：2024-11-14

    申请号：US18656894

    申请日：2024-05-07

    Applicant: NEC Laboratories America, Inc.

    Inventor： Alexandru Niculescu-Mizil ,  Konstantinos Dafnis

    IPC: G06N3/08

    Abstract: Methods and systems for deep learning include encoding input data, using a data encoder machine learning model, to generate an embedded representation of the input data. A correction is added to the input data with a rule encoder machine learning model to generate a corrected representation. The corrected representation is decoded using a data decoder machine learning model to generate a prediction. Parameters of the rule encoder machine learning model are updated using a loss function that encodes symbolic information relating to the prediction.

    Adaptive Convolutional Neural Knowledge Graph Learning System Leveraging Entity Descriptions
    7.
    发明申请
    Adaptive Convolutional Neural Knowledge Graph Learning System Leveraging Entity Descriptions 审中-公开

    公开(公告)号：US20190122111A1

    公开(公告)日：2019-04-25

    申请号：US16168244

    申请日：2018-10-23

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Bing Bai ,  Alexandru Niculescu-Mizil ,  Igor Durdanovic ,  Hans Peter Graf

    IPC: G06N3/08 ,  G06N5/02

    Abstract: Systems and methods for predicting new relationships in the knowledge graph, including embedding a partial triplet including a head entity description and a relationship or a tail entity description to produce a separate vector for each of the head, relationship, and tail. The vectors for the head entity, relationship, and tail entity can be combined into a first matrix, and adaptive kernels generated from the entity descriptions can be applied to the matrix through convolutions to produce a second matrix having a different dimension from the first matrix. An activation function can be applied to the second matrix to obtain non-negative feature maps, and max-pooling can be used over the feature maps to get subsamples. A fixed length vector, Z, flattens the subsampling feature maps into a feature vector, and a linear mapping method is used to map the feature vectors into a prediction score.

    RECONSTRUCTOR AND CONTRASTOR FOR ANOMALY DETECTION
    8.
    发明申请
    RECONSTRUCTOR AND CONTRASTOR FOR ANOMALY DETECTION 审中-公开

    公开(公告)号：US20180374207A1

    公开(公告)日：2018-12-27

    申请号：US15983342

    申请日：2018-05-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Alexandru Niculescu-Mizil ,  Eric Cosatto ,  Felix Wu

    IPC: G06T7/00 ,  H04N19/17 ,  H04N19/132

    Abstract: Systems and methods for detecting and correcting defective products include capturing at least one image of a product with at least one image sensor to generate an original image of the product. An encoder encodes portions of an image extracted from the original image to generate feature space vectors. A decoder decodes the feature space vectors to reconstruct the portions of the image into reconstructed portions by predicting defect-free structural features in each of the portions according to hidden layers trained to predict defect-free products. Each of the reconstructed portions are merged into a reconstructed image of a defect-free representation of the product. The reconstructed image is communicated to a contrastor to detect anomalies indicating defects in the product.

    Methods and systems for dependency network analysis using a multitask learning graphical lasso objective function
    9.
    发明授权
    Methods and systems for dependency network analysis using a multitask learning graphical lasso objective function 有权
    使用多任务学习图形套索目标函数的依赖网络分析的方法和系统

    公开(公告)号：US09449284B2

    公开(公告)日：2016-09-20

    申请号：US14049891

    申请日：2013-10-09

    Applicant: NEC Laboratories America, Inc.

    Inventor： Alexandru Niculescu-Mizil ,  Diane Oyen

    IPC: G06F15/18 ,  G06N99/00 ,  G06N7/00 ,  G06F19/12 ,  G06F19/20 ,  G06F19/26

    CPC classification number: G06N99/005 ,  G06F19/12 ,  G06F19/20 ,  G06F19/26 ,  G06N7/005

    Abstract: Methods and systems for displaying dependencies within data and illustrating differences between a plurality of data sets are disclosed. In accordance with one such method, a plurality of data sets are received for the generation of a plurality of dependency networks in accordance with a graphical modeling scheme. The method further includes receiving a selection of a value of a parameter that adjusts a number of differences between the dependency networks in accordance with the graphical modeling scheme. In addition, at least one version of the dependency networks is generated based on the selected value of the parameter. Further, the one or more versions of the dependency networks is output to permit a user to analyze distinctions between the dependency networks.

    Abstract translation: 公开了用于在数据中显示依赖性并示出多个数据集之间的差异的方法和系统。 根据一种这样的方法，接收多个数据集用于根据图形建模方案生成多个依赖网络。 该方法还包括接收根据图形建模方案来调整依赖性网络之间的差异数量的参数的值的选择。 另外，基于所选择的参数值生成至少一个版本的依赖关系网络。 此外，输出依赖网络的一个或多个版本以允许用户分析依赖性网络之间的区别。

Patent Agency Ranking