Patents by Inventor Lu Ran

Lu Ran 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: 11106951
    Abstract: A bidirectional image-text retrieval method based on a multi-view joint embedding space includes: performing retrieval with reference to a semantic association relationship at a global level and a local level, obtaining the semantic association relationship at the global level and the local level in a frame-sentence view and a region-phrase view, and obtaining semantic association information in a global level subspace of frame and sentence in the frame-sentence view, obtaining semantic association information in a local level subspace of region and phrase in the region-phrase view, processing data by a dual-branch neural network in the two views to obtain an isomorphic feature and embedding the same in a common space, and using a constraint condition to reserve an original semantic relationship of the data during training, and merging the two semantic association relationships using multi-view merging and sorting to obtain a more accurate semantic similarity between data.
    Type: Grant
    Filed: January 29, 2018
    Date of Patent: August 31, 2021
    Assignee: Peking University Shenzhen Graduate Sohool
    Inventors: Wenmin Wang, Lu Ran, Ronggang Wang, Ge Li, Shengfu Dong, Zhenyu Wang, Ying Li, Hui Zhao, Wen Gao
  • Publication number: 20210150255
    Abstract: A bidirectional image-text retrieval method based on a multi-view joint embedding space includes: performing retrieval with reference to a semantic association relationship at a global level and a local level, obtaining the semantic association relationship at the global level and the local level in a frame-sentence view and a region-phrase view, and obtaining semantic association information in a global level subspace of frame and sentence in the frame-sentence view, obtaining semantic association information in a local level subspace of region and phrase in the region-phrase view, processing data by a dual-branch neural network in the two views to obtain an isomorphic feature and embedding the same in a common space, and using a constraint condition to reserve an original semantic relationship of the data during training, and merging the two semantic association relationships using multi-view merging and sorting to obtain a more accurate semantic similarity between data.
    Type: Application
    Filed: January 29, 2018
    Publication date: May 20, 2021
    Inventors: Wenmin Wang, Lu Ran, Ronggang Wang, Ge Li, Shengfu Dong, Zhenyu Wang, Ying Li, Hui Zhao, Wen Gao
  • Patent number: 10134744
    Abstract: A semiconductor memory device includes a first inverter, a second inverter, a first and second inner access transistors, and a first and second outer access transistors. The first inverter includes a first pull-up transistor and a first pull-down transistor, the second inverter includes a second pull-up transistor (PL2) and a second pull-down transistor, and the first inverter and the second inverter forms a latch circuit. The first and second inner access transistors and the first and second outer access transistors are electrically connected to the latch circuit, and channel widths of the second inner access transistor and the second outer access transistor are different from each other.
    Type: Grant
    Filed: August 21, 2017
    Date of Patent: November 20, 2018
    Assignee: UNITED MICROELECTRONICS CORP.
    Inventors: Chih-Han Chen, Wei-Chi Chen, Ching Chang, Ming-Shing Chen, Chao-Hsien Wu, Chia-Hui Hwang, Lu-Ran Huang