知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

18 records (took 0.04 seconds)

    AUTOMATED GENERATION OF PRE-LABELED TRAINING DATA
    1.
    发明申请
    AUTOMATED GENERATION OF PRE-LABELED TRAINING DATA 审中-公开

    公开(公告)号：US20190156487A1

    公开(公告)日：2019-05-23

    申请号：US16258037

    申请日：2019-01-25

    Applicant: Cisco Technology, Inc.

    Inventor： Rob Liston ,  John G. Apostolopoulos

    IPC: G06T7/11 ,  G06T11/00 ,  G06T7/194

    Abstract: Presented herein are techniques for automatically generating object segmentation training data. In particular, a segmentation data generation system is configured to obtain training images derived from a scene captured by one or more image capture devices. Each training image is a still image that includes a foreground object and a background. The segmentation data generation system automatically generates a mask of the training image to delineate the object from the background and, based on the mask automatically generates a masked image. The masked image includes only the object present in the training image. The segmentation data generation system composites the masked image with an image of an environmental scene to generate a composite image that includes the masked image and the environmental scene.

    CLUSTERING-BASED PERSON RE-IDENTIFICATION
    3.
    发明申请
    CLUSTERING-BASED PERSON RE-IDENTIFICATION 审中-公开

    公开(公告)号：US20180204093A1

    公开(公告)日：2018-07-19

    申请号：US15409821

    申请日：2017-01-19

    Applicant: Cisco Technology, Inc.

    Inventor： Xiaoqing Zhu ,  Rob Liston ,  John G. Apostolopoulos ,  Wai-tian Tan

    IPC: G06K9/62 ,  G06K9/00 ,  G06F17/30

    CPC classification number: G06K9/6218 ,  G06F17/30256 ,  G06F17/3028 ,  G06K9/00295 ,  G06K9/00771 ,  G06K9/6215

    Abstract: Presented herein are techniques for assignment of an identity to a group of captured images. A plurality of captured images that each include an image of at least one person are obtained. For each of the plurality of captured images, relational metrics indicating a relationship between the image of the person in a respective captured image and the images of the persons in each of the remaining plurality of captured images is calculated. Based on the relational metrics, a clustering process is performed to generate one or more clusters from the plurality of captured images. Each of the one or more clusters are associated with an identity of an identity database. The one or more clusters may each be associated with an existing identity of the identity database or an additional identity that is not yet present in the identity database.

    Training distributed machine learning with selective data transfers
    5.
    发明授权
    Training distributed machine learning with selective data transfers 有权

    公开(公告)号：US11144616B2

    公开(公告)日：2021-10-12

    申请号：US15439072

    申请日：2017-02-22

    Applicant: Cisco Technology, Inc.

    Inventor： Wai-tian Tan ,  Rob Liston ,  John G. Apostolopoulos ,  Xiaoqing Zhu

    IPC: G06F17/18 ,  G06F9/46 ,  G06N3/04 ,  G06N3/08 ,  G06N3/063 ,  G06N5/00

    Abstract: Presented herein are techniques for training a central/global machine learning model in a distributed machine learning system. In the data sampling techniques, a subset of the data obtained at the local sites is intelligently selected for transfer to the central site for use in training the central machine learning model. In the model merging techniques, distributed local training occurs in each local site and copies of the local machine learning models are sent to the central site for aggregation of learning by merging of the models. As a result, in accordance with the examples presented herein, a central machine learning model can be trained based on various representations/transformations of data seen at the local machine learning models, including sampled selections of data-label pairs, intermediate representation of training errors, or synthetic data-label pairs generated by models trained at various local sites.

    Automated generation of pre-labeled training data
    6.
    发明授权
    Automated generation of pre-labeled training data 有权

    公开(公告)号：US10242449B2

    公开(公告)日：2019-03-26

    申请号：US15397987

    申请日：2017-01-04

    Applicant: Cisco Technology, Inc.

    Inventor： Rob Liston ,  John G. Apostolopoulos

    IPC: G06T7/11

    Abstract: Presented herein are techniques for automatically generating object segmentation training data. In particular, a segmentation data generation system is configured to obtain training images derived from a scene captured by one or more image capture devices. Each training image is a still image that includes a foreground object and a background. The segmentation data generation system automatically generates a mask of the training image to delineate the object from the background and, based on the mask automatically generates a masked image. The masked image includes only the object present in the training image. The segmentation data generation system composites the masked image with an image of an environmental scene to generate a composite image that includes the masked image and the environmental scene.

    REAL-TIME UPDATES TO MAPS FOR AUTONOMOUS NAVIGATION
    7.
    发明申请
    REAL-TIME UPDATES TO MAPS FOR AUTONOMOUS NAVIGATION 审中-公开

    公开(公告)号：US20180299274A1

    公开(公告)日：2018-10-18

    申请号：US15488945

    申请日：2017-04-17

    Applicant: Cisco Technology, Inc.

    Inventor： Ashok K. Moghe ,  John G. Apostolopoulos ,  Avraham A. Poupko

    IPC: G01C21/32 ,  G06F17/30 ,  H04L29/08

    Abstract: Presented herein are techniques for updating detailed maps used to navigate an autonomous vehicle. The techniques include determining that a vehicle has come within a predetermined range of a road side unit, establishing a communication link with the vehicle, receiving, from the vehicle, data sufficient to identify a vehicle type of the vehicle, based on the vehicle type, selecting a map, stored by the road side unit, for the vehicle, sending a query to a neighbor road side unit seeking data to augment the map, in response to the query, receiving the data to augment the map from the neighbor road side unit, updating the map based on the data to augment the map to obtain an updated map, and sending at least a aspects of the updated map to the vehicle.

    Clustering-based person re-identification
    9.
    发明授权
    Clustering-based person re-identification 有权

    公开(公告)号：US10275683B2

    公开(公告)日：2019-04-30

    申请号：US15409821

    申请日：2017-01-19

    Applicant: Cisco Technology, Inc.

    Inventor： Xiaoqing Zhu ,  Rob Liston ,  John G. Apostolopoulos ,  Wai-tian Tan

    IPC: G06K9/00 ,  G06K9/62 ,  G06F17/30

    Abstract: Presented herein are techniques for assignment of an identity to a group of captured images. A plurality of captured images that each include an image of at least one person are obtained. For each of the plurality of captured images, relational metrics indicating a relationship between the image of the person in a respective captured image and the images of the persons in each of the remaining plurality of captured images is calculated. Based on the relational metrics, a clustering process is performed to generate one or more clusters from the plurality of captured images. Each of the one or more clusters are associated with an identity of an identity database. The one or more clusters may each be associated with an existing identity of the identity database or an additional identity that is not yet present in the identity database.

    TRACKING APPLICATION SCALING FOR NETWORK BANDWIDTH ALLOCATION
    10.
    发明公开
    TRACKING APPLICATION SCALING FOR NETWORK BANDWIDTH ALLOCATION 审中-公开

    公开(公告)号：US20240163226A1

    公开(公告)日：2024-05-16

    申请号：US18421906

    申请日：2024-01-24

    Applicant: Cisco Technology, Inc.

    Inventor： Lorand Jakab ,  Alberto Rodriguez-Natal ,  Fabio R. Maino ,  John G. Apostolopoulos

    IPC: H04L47/783 ,  G06F9/54

    CPC classification number: H04L47/783 ,  G06F9/547

    Abstract: Techniques for tracking compute capacity of a scalable application service platform to perform dynamic bandwidth allocation for data flows associated with applications hosted by the service platform are disclosed. Some of the techniques may include allocating a first amount of bandwidth of a physical underlay of a network for data flows associated with an application. The techniques may also include receiving, from a scalable application service hosting the application, an indication of an amount of computing resources of the scalable application service that are allocated to host the application. Based at least in part on the indications, a second amount of bandwidth of the physical underlay to allocate for the data flows may be determined. The techniques may also include allocating the second amount of bandwidth of the physical underlay of the network for the data flows associated with the application.

Patent Agency Ranking