Patents by Inventor Dongliang Chang

Dongliang Chang 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: 11501518
    Abstract: The present disclosure provides a fine-grained image recognition method, an electronic device and a computer readable storage medium. The method comprises the steps of feature extraction, calculation of feature discriminant loss function, calculation of feature diversity loss function and calculation of model optimization loss function. The present disclosure comprehensively considers influences of factors such as a large intra-class difference, a small inter-class difference, and a great influence of background noise of the fine-grained image, and makes constrains such that the feature maps belonging to each class are discriminative and have the features of corresponding class, thus reducing the intra-class difference, decreasing the learning difficulty and learning better discriminative features.
    Type: Grant
    Filed: September 30, 2020
    Date of Patent: November 15, 2022
    Assignee: Beijing University of Posts and Telecommunications
    Inventors: Zhanyu Ma, Dongliang Chang, Jiyang Xie, Yifeng Ding, Zhongwei Si
  • Publication number: 20210133479
    Abstract: The present disclosure provides a fine-grained image recognition method, an electronic device and a computer readable storage medium. The method comprises the steps of feature extraction, calculation of feature discriminant loss function, calculation of feature diversity loss function and calculation of model optimization loss function. The present disclosure comprehensively considers influences of factors such as a large intra-class difference, a small inter-class difference, and a great influence of background noise of the fine-grained image, and makes constrains such that the feature maps belonging to each class are discriminative and have the features of corresponding class, thus reducing the intra-class difference, decreasing the learning difficulty and learning better discriminative features.
    Type: Application
    Filed: September 30, 2020
    Publication date: May 6, 2021
    Inventors: Zhanyu MA, Dongliang CHANG, Jiyang XIE, Yifeng DING, Zhongwei SI
  • Publication number: 20040029237
    Abstract: A process for the preparation of N-substituted 4-hydroxypiperidine, wherein an oxygen atom is inserted regioselectively into the corresponding N-substituted piperidine, by using as a biocatalyst a bacterium degrading alkanes or alicyclic hydrocarbons, or a prokaryotic host-organism having the gene(s) necessary for the hydroxylation derived from the said bacterium, or an enzyme having hydroxylation activity derived therefrom. The bacterium may be selected from species from, for example, the genera Sphingomonas and Pseudomonas, that are capable of degrading n-alkanes having 4 to 20 carbon atoms.
    Type: Application
    Filed: August 21, 2003
    Publication date: February 12, 2004
    Inventors: Zhi Li, Dongliang Chang, Bernard Witholt
  • Publication number: 20040009562
    Abstract: This invention provides a process for the preparation of optically active 4-hydroxy-2-pyrrolidinone or N-substituted 4-hydroxy-2-pyrrolidinones, wherein an oxygen atom is inserted regio- and stereoselectively into the corresponding non-hydroxylated 2-pyrrolidinones, by using, as a biocatalyst, a microorganism having hydroxylation activity, or a host-organism having the gene(s) necessary for the hydroxylation enzymes derived from the said microorganism, or an enzyme having hydroxylation activity derived from the above microorganisms. The microorganism may be selected from the group consisting of microorganisms that degrade alkanes or cyclic hydrocarbons, microorganisms having alkane hydroxylase(s), or microorganisms that are able to oxidize hydrocarbons.
    Type: Application
    Filed: July 21, 2003
    Publication date: January 15, 2004
    Inventors: Zhi Li, Dongliang Chang, Bernard Witholt