Patents by Inventor Dengke Dong

Dengke Dong has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250013309
    Abstract: Disclosed are a virtual object display method and apparatus, an electronic device, and a readable medium. The method comprises: recognizing a trigger gesture from hand images according to three-dimensional coordinates of a hand key point, the hand images comprising at least two continuous frames of first hand images in which the hand key point is relatively stationary, at least one frame of a second hand image in which the hand key point moving relative to the first hand image, and a gesture of at least one of the first hand images and the second hand image being the trigger gesture; in response to the trigger gesture, determining a throwing parameter according to the hand images; simulating a trajectory of a thrown virtual object according to the throwing parameter and displaying the trajectory in an augmented reality scene.
    Type: Application
    Filed: November 2, 2022
    Publication date: January 9, 2025
    Inventors: Qingwen Hu, Hang Zhao, Gaojie Lin, Dengke Dong
  • Patent number: 11062180
    Abstract: Methods and systems for training machine vision models (MVMs) with “noisy” training datasets are described. A noisy set of images is received, where labels for some of the images are “noisy” and/or incorrect. A progressively-sequenced learning curriculum is designed for the noisy dataset, where the images that are easiest to learn machine-vision knowledge from are sequenced near the beginning of the curriculum and images that are harder to learn machine-vision knowledge from are sequenced later in the curriculum. An MVM is trained via providing the sequenced curriculum to a supervised learning method, so that the MVM learns from the easiest examples first and the harder training examples later, i.e., the MVM progressively accumulates knowledge from simplest to most complex. To sequence the curriculum, the training images are embedded in a feature space and the “complexity” of each image is determined via density distributions and clusters in the feature space.
    Type: Grant
    Filed: July 18, 2018
    Date of Patent: July 13, 2021
    Assignee: Shenzhen Malong Technologies Co., Ltd.
    Inventors: Sheng Guo, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, Dengke Dong, Matthew R. Scott, Dinglong Huang
  • Publication number: 20210125001
    Abstract: Methods and systems for training machine vision models (MVMs) with “noisy” training datasets are described. A noisy set of images is received, where labels for some of the images are “noisy” and/or incorrect. A progressively-sequenced learning curriculum is designed for the noisy dataset, where the images that are easiest to learn machine-vision knowledge from are sequenced near the beginning of the curriculum and images that are harder to learn machine-vision knowledge from are sequenced later in the curriculum. An MVM is trained via providing the sequenced curriculum to a supervised learning method, so that the MVM learns from the easiest examples first and the harder training examples later, i.e., the MVM progressively accumulates knowledge from simplest to most complex. To sequence the curriculum, the training images are embedded in a feature space and the “complexity” of each image is determined via density distributions and clusters in the feature space.
    Type: Application
    Filed: July 18, 2018
    Publication date: April 29, 2021
    Inventors: Sheng Guo, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, Dengke Dong, Matthew R. Scott, Dinlong Huang