利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

5 条记录 (耗时 0.013 秒)

    AUTOENCODING GENERATIVE ADVERSARIAL NETWORK FOR AUGMENTING TRAINING DATA USABLE TO TRAIN PREDICTIVE MODELS
    1.
    发明申请
    AUTOENCODING GENERATIVE ADVERSARIAL NETWORK FOR AUGMENTING TRAINING DATA USABLE TO TRAIN PREDICTIVE MODELS 有权

    公开(公告)号：US20210256353A1

    公开(公告)日：2021-08-19

    申请号：US17056272

    申请日：2019-05-13

    申请人： Tobii AB

    发明人： Mårten Nilsson

    IPC分类号： G06N3/04 ,  G06N3/08 ,  G06K9/62

    摘要： Techniques for using a deep generative model to generate synthetic data sets that can be used to boost the performance of a discriminative model are described. In an example, an autoencoding generative adversarial network (AEGAN) is trained to generate the synthetic data sets. The AEGAN includes an autoencoding network and a generative adversarial network (GAN) that share a generator. The generator learns how to the generate synthetic data sets based on a data distribution from a latent space. Upon training the AEGAN, the generator generates the synthetic data sets. In turn, the synthetic data sets arc used to train a predictive model, such as a convolutional neural network for gaze prediction.

    TRAINING AN EYE TRACKING MODEL
    2.
    发明申请
    TRAINING AN EYE TRACKING MODEL 有权

    公开(公告)号：US20210012157A1

    公开(公告)日：2021-01-14

    申请号：US16834153

    申请日：2020-03-30

    申请人： Tobii AB

    发明人： Carl Asplund ,  Patrik Barkman ,  Anders Dahl ,  Oscar Danielsson ,  Tommaso Martini ,  Mårten Nilsson

    IPC分类号： G06K9/62 ,  G06K9/00 ,  G06K9/20

    摘要： A method for training an eye tracking model is disclosed, as well as a corresponding system and storage medium. The eye tracking model is adapted to predict eye tracking data based on sensor data from a first eye tracking sensor. The method comprises receiving sensor data obtained by the first eye tracking sensor at a time instance and receiving reference eye tracking data for the time instance generated by an eye tracking system comprising a second eye tracking sensor. The reference eye tracking data is generated by the eye tracking system based on sensor data obtained by the second eye tracking sensor at the time instance. The method comprises training the eye tracking model based on the sensor data obtained by the first eye tracking sensor at the time instance and the generated reference eye tracking data.

    Training an eye tracking model
    4.
    发明授权
    Training an eye tracking model 有权

    公开(公告)号：US11386290B2

    公开(公告)日：2022-07-12

    申请号：US16834153

    申请日：2020-03-30

    申请人： Tobii AB

    发明人： Carl Asplund ,  Patrik Barkman ,  Anders Dahl ,  Oscar Danielsson ,  Tommaso Martini ,  Mårten Nilsson

    IPC分类号： G06K9/62 ,  G06V10/145 ,  G06V40/19

    摘要： A method for training an eye tracking model is disclosed, as well as a corresponding system and storage medium. The eye tracking model is adapted to predict eye tracking data based on sensor data from a first eye tracking sensor. The method comprises receiving sensor data obtained by the first eye tracking sensor at a time instance and receiving reference eye tracking data for the time instance generated by an eye tracking system comprising a second eye tracking sensor. The reference eye tracking data is generated by the eye tracking system based on sensor data obtained by the second eye tracking sensor at the time instance. The method comprises training the eye tracking model based on the sensor data obtained by the first eye tracking sensor at the time instance and the generated reference eye tracking data.