Patents by Inventor Guangzhi WANG

Guangzhi WANG 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).

  • Patent number: 11526807
    Abstract: Embodiments of the disclosure provide systems and methods for domain adaptation between a plurality of source domains and a target domain. The artificial intelligence method includes receiving labeled data from the plurality of source domains and unlabeled data from the target domain. The method further includes separately training, by a processor, a plurality of source classifiers each corresponding to a source domain using the labeled data received from the respective source domains. The method also includes selecting a subset of the labeled data received from each source domain based on a similarity between the selected labeled data and the unlabeled data of the target domain. The method additionally includes refining, by the processor, each source classifier using the selected subset of the labeled data, and predicting labels of the unlabeled data using the refined source classifiers.
    Type: Grant
    Filed: March 20, 2020
    Date of Patent: December 13, 2022
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Pengfei Xu, Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Runbo Hu, Hua Chai
  • Publication number: 20210295208
    Abstract: Embodiments of the disclosure provide systems and methods for domain adaptation between a plurality of source domains and a target domain. The artificial intelligence method includes receiving labeled data from the plurality of source domains and unlabeled data from the target domain. The method further includes separately training, by a processor, a plurality of source classifiers each corresponding to a source domain using the labeled data received from the respective source domains. The method also includes selecting a subset of the labeled data received from each source domain based on a similarity between the selected labeled data and the unlabeled data of the target domain. The method additionally includes refining, by the processor, each source classifier using the selected subset of the labeled data, and predicting labels of the unlabeled data using the refined source classifiers.
    Type: Application
    Filed: March 20, 2020
    Publication date: September 23, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Pengfei Xu, Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Runbo Hu, Hua Chai
  • Patent number: 10751030
    Abstract: The present application relates to an ultrasound fusion imaging method and an ultrasound fusion image navigation system. The ultrasound fusion imaging method includes a selection step, a registration step and a fusion step. The selection step is for selecting at least one ultrasound image from at least one previously stored piece of ultrasound video data according to an input instruction. The ultrasound video data includes an ultrasound image obtained by acquiring a target object in at least one plane and position indicating information corresponding to the ultrasound image. The registration step is for registering the selected at least one ultrasound image with a modality image. The registration process uses the location of the position indicating information of the at least one ultrasound image. The fusion step is for fusing the registered ultrasound image with the modality image.
    Type: Grant
    Filed: April 8, 2016
    Date of Patent: August 25, 2020
    Assignees: SHENZHEN MINDRAY BIO-MEDICAL ELECTRONICS CO., LTD., TSINGHUA UNIVERSITY
    Inventors: Jingang Kang, Guangzhi Wang, Lei Zhu, Qian Zhang, Hui Ding, Minglei Yang, Longfei Cong
  • Publication number: 20170020489
    Abstract: The present application relates to an ultrasound fusion imaging method and an ultrasound fusion image navigation system. The ultrasound fusion imaging method includes a selection step, a registration step and a fusion step. The selection step is for selecting at least one ultrasound image from at least one previously stored piece of ultrasound video data according to an input instruction. The ultrasound video data includes an ultrasound image obtained by acquiring a target object in at least one plane and position indicating information corresponding to the ultrasound image. The registration step is for registering the selected at least one ultrasound image with a modality image. The registration process uses the location of the position indicating information of the at least one ultrasound image. The fusion step is for fusing the registered ultrasound image with the modality image.
    Type: Application
    Filed: April 8, 2016
    Publication date: January 26, 2017
    Inventors: Jingang KANG, Guangzhi WANG, Lei ZHU, Qian ZHANG, Hui DING, Minglei YANG, Longfei CONG