Patents by Inventor Zhenyu Zhong

Zhenyu Zhong 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: 11138964
    Abstract: According to various embodiments, an end-to-end TTS framework can integrate a watermarking process into the training of the TTS framework, which enables watermarks to be imperceptible within a synthesized/cloned audio segment generated by the TTS framework. The watermarks added in such a matter are statistically undetectable to prevent authorized removal. According to an exemplary method of training the TTS framework, a TTS neural network model and a watermarking neural network mode in the TTS framework are trained in an end to end manner, with the watermarking being part of the optimization process of the TTS framework. During the training, neuron values of the TTS neural network model are adjusted based on training data to prepare one or more spaces for adding a watermark in a synthesized audio segment to be generated by the TTS framework.
    Type: Grant
    Filed: October 21, 2019
    Date of Patent: October 5, 2021
    Assignee: BAIDU USA LLC
    Inventors: Wei Ping, Zhenyu Zhong, Yueqiang Cheng, Xing Li, Tao Wei
  • Publication number: 20210154222
    Abstract: Provided herein are methods of treating NLRP3 inflammasome-associated diseases and disorders. Also, disclosed are methods for screening for agents useful in such methods.
    Type: Application
    Filed: November 12, 2020
    Publication date: May 27, 2021
    Inventors: Michael Karin, Zhenyu Zhong
  • Patent number: 10990855
    Abstract: In one embodiment, a system receives a first image captured by a capturing device of an ADV. The system applies an image transformation to the first image to generate a second image. The system applies an object detection model to the first and the second images to generate a first and a second output, respectively. The system calculates a similarity metric between the first and the second output. The system detects the first image as an adversarial sample if a temporal variation of the similarity metric between the first image and a prior image is above a threshold.
    Type: Grant
    Filed: June 13, 2019
    Date of Patent: April 27, 2021
    Assignee: BAIDU USA LLC
    Inventors: Yunhan Jia, Zhenyu Zhong, Yulong Zhang, Tao Wei
  • Publication number: 20210118423
    Abstract: According to various embodiments, an end-to-end TTS framework can integrate a watermarking process into the training of the TTS framework, which enables watermarks to be imperceptible within a synthesized/cloned audio segment generated by the TTS framework. The watermarks added in such a matter are statistically undetectable to prevent authorized removal. According to an exemplary method of training the TTS framework, a TTS neural network model and a watermarking neural network mode in the TTS framework are trained in an end to end manner, with the watermarking being part of the optimization process of the TTS framework. During the training, neuron values of the TTS neural network model are adjusted based on training data to prepare one or more spaces for adding a watermark in a synthesized audio segment to be generated by the TTS framework.
    Type: Application
    Filed: October 21, 2019
    Publication date: April 22, 2021
    Inventors: Wei PING, Zhenyu ZHONG, Yueqiang CHENG, Xing LI, Tao WEI
  • Publication number: 20210062270
    Abstract: Methods and compositions are provided for oligonucleotides that bind target biomarkers and allow characterization of a phenotype. The target biomarkers may include microvesicle antigens, including microvesicles derived from various diseases. The characterization may comprise detection, diagnosis, prognosis, theranosis or other characterization of a disease or disorder.
    Type: Application
    Filed: July 23, 2020
    Publication date: March 4, 2021
    Inventors: David Spetzler, Valeriy Domenyuk, Nianqing Xiao, Adam Stark, Zhenyu Zhong
  • Patent number: 10936705
    Abstract: Embodiments of the present disclosure disclose an authentication method, an electronic device, and a computer-readable program medium. A specific embodiment of the method comprises: acquiring multimedia input information of a user in response to receiving an authentication request from the user; parsing the multimedia input information to obtain a parsing result; authenticating the user based on the parsing result; and transmitting an authentication result to the user; wherein the multimedia input information includes human face video input information and voice input information of the user; and the parsing result includes at least two of: biometric feature information of the user, voice content information, and behavior feature information of the user. The embodiments may lower a risk that a hacker forges the information for authentication inputted by the user.
    Type: Grant
    Filed: October 31, 2017
    Date of Patent: March 2, 2021
    Assignee: BAIDU USA LLC
    Inventors: Zhebin Qiu, Tao Wei, Zhenyu Zhong
  • Patent number: 10869880
    Abstract: Provided herein are methods of treating NLRP3 inflammasome-associated diseases and disorders. Also, disclosed are methods for screening for agents useful in such methods.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: December 22, 2020
    Assignee: The Regents of the University of California
    Inventors: Michael Karin, Zhenyu Zhong
  • Publication number: 20200394466
    Abstract: Embodiments of the disclosure disclose a system to mitigate against adversarial input samples for machine learning (ML)/artificial intelligence (AI) models. According to one embodiment, a system receives a query from a client for a ML service. The system calculates a similarity score for the query based on a number of prior queries received from the client, the similarity score representing a similarity between the received query and the prior queries. The system determines that the query is an adversarial query in response to determining that the similarity score is above a predetermined threshold.
    Type: Application
    Filed: June 13, 2019
    Publication date: December 17, 2020
    Inventors: Yunhan JIA, Zhenyu ZHONG, Yulong ZHANG, Tao WEI
  • Publication number: 20200394472
    Abstract: In one embodiment, a system receives a first image captured by a capturing device of an ADV. The system applies an image transformation to the first image to generate a second image. The system applies an object detection model to the first and the second images to generate a first and a second output, respectively. The system calculates a similarity metric between the first and the second output. The system detects the first image as an adversarial sample if a temporal variation of the similarity metric between the first image and a prior image is above a threshold.
    Type: Application
    Filed: June 13, 2019
    Publication date: December 17, 2020
    Inventors: Yunhan JIA, Zhenyu ZHONG, Yulong ZHANG, Tao WEI
  • Patent number: 10833054
    Abstract: Emitter panels and displays utilizing solid state packages and methods for fabricating the same are disclosed. One emitter panel comprises a raised barrier on a submount defining a plurality of cavities, each cavity having at least one LED in a pixel area. The panel is capable of receiving electrical signals for independently controlling the emission from the emitters. Solid state displays utilize the emitter panels mounted in relation to one another to generate a message or image. The panels comprise multiple pixels each having at least one light emitter, with each panel capable of receiving electrical signals for independently controlling the emission of at the pixels.
    Type: Grant
    Filed: February 8, 2014
    Date of Patent: November 10, 2020
    Inventors: Chi Keung Alex Chan, Zhenyu Zhong, Chak Hau Charles Pang, Yue Kwong Victor Lau, Erzhuang Liu
  • Publication number: 20200270610
    Abstract: Methods and compositions are provided for oligonucleotide probes and oligonucleotide probe libraries that recognize targets of interest. The targets include circulating biomarkers such as microvesicles, including those derived from various diseases.
    Type: Application
    Filed: November 25, 2019
    Publication date: August 27, 2020
    Applicant: Caris Science, Inc.
    Inventors: Valeriy DOMENYUK, Adam STARK, Nianqing XIAO, Zhenyu ZHONG, Mark MIGLARESE, David SPETZLER
  • Patent number: 10751398
    Abstract: Compositions and treatments for inducing tumor regression by activating inflammasomes in tumor cells and tumor-associated cells. A tumor in a subject is treated by administering a composition to the subject that activates inflammasomes in cells of the tumor and thereby causes tumor cell pyroptosis and tumor regression.
    Type: Grant
    Filed: October 9, 2017
    Date of Patent: August 25, 2020
    Assignee: Loyola University Chicago
    Inventors: Liang Qiao, Zhenyu Zhong, Yougang Zhai
  • Patent number: 10729117
    Abstract: The present invention relates to a pest monitoring method based on machine vision. The method includes the following steps: arranging a pest trap at a place where pests gather, and setting an image acquisition device in front of the pest trap to acquire an image; identifying a pest in the acquired image, and obtaining a number of pests; extracting multiple suspicious pest images from a region of each identified pest in the image, and determining identification accuracy of each suspicious pest image, if the number of pests is greater than or equal to a preset threshold for the number of pests; and calculating a predicted level of pest damage based on the number of pests and the identification accuracy of each suspicious pest image. The present invention acquires a pest image automatically through the image acquisition device in front of the pest trap.
    Type: Grant
    Filed: December 25, 2017
    Date of Patent: August 4, 2020
    Assignee: ZHONGKAI UNIVERSITY OF AGRICULTURE AND ENGINEER
    Inventors: Yu Tang, Shaoming Luo, Zhenyu Zhong, Huan Lei, Chaojun Hou, Jiajun Zhuang, Weifeng Huang, Zaili Chen, Jintian Lin, Lixue Zhu
  • Publication number: 20200178511
    Abstract: The present invention relates to a pest monitoring method based on machine vision. The method includes the following steps: arranging a pest trap at a place where pests gather, and setting an image acquisition device in front of the pest trap to acquire an image; identifying a pest in the acquired image, and obtaining a number of pests; extracting multiple suspicious pest images from a region of each identified pest in the image, and determining identification accuracy of each suspicious pest image, if the number of pests is greater than or equal to a preset threshold for the number of pests; and calculating a predicted level of pest damage based on the number of pests and the identification accuracy of each suspicious pest image. The present invention acquires a pest image automatically through the image acquisition device in front of the pest trap.
    Type: Application
    Filed: December 25, 2017
    Publication date: June 11, 2020
    Inventors: Yu TANG, Shaoming LUO, Zhenyu ZHONG, Huan LEI, Chaojun HOU, Jiajun ZHUANG, Weifeng HUANG, Zaili CHEN, Jintian LIN, Lixue ZHU
  • Patent number: 10679973
    Abstract: Emitter packages and LEDs displays utilizing the packages are disclosed, with the packages providing advantages such as reducing the cost and interconnect complexity for the packages and displays. One emitter package comprises a casing with a plurality of cavities, each cavity having at least one LED. A lead frame structure is included integral to the casing, with the at least one LED from each of the cavities mounted to the lead frame structure. The package is capable of receiving electrical signals for independently controlling the emission from a first and second of the cavities. One LED display utilizes the LED packages mounted in relation to one another to generate a message or image. The LED packages comprise multiple pixels each having at least one LED, with each package capable of receiving electrical signals for independently controlling the emission of at least a first and second of the pixels.
    Type: Grant
    Filed: June 13, 2017
    Date of Patent: June 9, 2020
    Assignee: Cree Huizhou Solid State Lighting Company Limited
    Inventors: Chak Hau Charles Pang, Chi Keung Alex Chan, David Emerson, Yue Kwong Victor Lau, Zhenyu Zhong
  • Patent number: 10635893
    Abstract: Embodiments of the present disclosure disclose an identity authentication method, a terminal device, and a computer-readable storage medium. An embodiment of the method comprises: acquiring video data displaying a lip part mouth shape changing process of a user; parsing the video data to generate annotation information of a human face region displayed by each image in consecutive images constituting the video data and human face feature information corresponding to each image in the consecutive images; generating a lip part feature information sequence and a human face local part feature information sequence based on the generated annotation information and the consecutive images; and transmitting the generated human face feature information, the lip part feature information sequence, and the human face local part feature information sequence to a server, and receiving an identity verification result returned from the server. The embodiment enhances identity authentication security.
    Type: Grant
    Filed: October 31, 2017
    Date of Patent: April 28, 2020
    Assignee: Baidu USA LLC
    Inventors: Zhenyu Zhong, Tao Wei, Zhebin Qiu
  • Patent number: 10615324
    Abstract: A side view surface mount light emitting device is disclosed. The light emitting device comprises a side oriented package comprising a floor and a plurality of light emitting diodes (LEDs) mounted on the floor. The device further includes a plurality of contact pins in electrical contact, such that the plurality of contact pins protrude from a side of the package, in which at least one of the contact pins is oriented in a direction opposite the remaining contact pins. The LEDs of the device are disposed to emit light in a direction parallel to said mount surface. Some configurations also include a plurality of bond pads, on or a part of the floor, to facilitate electrical connection between the LEDs and the contact pins, in which adjacent bond pads have a tapered shape such that the widest portion of a first bond pad is adjacent to the narrowest portion of a second bond pad. Displays including such devices are also disclosed.
    Type: Grant
    Filed: June 11, 2014
    Date of Patent: April 7, 2020
    Assignee: Cree Huizhou Solid State Lighting Company Limited
    Inventors: Chi Keung Alex Chan, Yue Kwong Victor Lau, Chak Hau Charles Pang, Zhenyu Zhong
  • Publication number: 20190388454
    Abstract: Provided herein are methods of treating NLRP3 inflammasome-associated diseases and disorders. Also, disclosed are methods for screening for agents useful in such methods.
    Type: Application
    Filed: June 25, 2019
    Publication date: December 26, 2019
    Inventors: Michael Karin, Zhenyu Zhong
  • Publication number: 20190310172
    Abstract: Methods and compositions are provided for enriching extracellular vesicles, e.g., from bodily fluids. The vesicles may be indicative of various diseases. Vesicle characterization can be used for diagnostic, theranostic and other purposes.
    Type: Application
    Filed: April 5, 2019
    Publication date: October 10, 2019
    Inventors: Zhenyu ZHONG, David SPETZLER
  • Publication number: 20190130172
    Abstract: Embodiments of the present disclosure disclose an identity authentication method, a terminal device, and a computer-readable storage medium. An embodiment of the method comprises: acquiring video data displaying a lip part mouth shape changing process of a user; parsing the video data to generate annotation information of a human face region displayed by each image in consecutive images constituting the video data and human face feature information corresponding to each image in the consecutive images; generating a lip part feature information sequence and a human face local part feature information sequence based on the generated annotation information and the consecutive images; and transmitting the generated human face feature information, the lip part feature information sequence, and the human face local part feature information sequence to a server, and receiving an identity verification result returned from the server. The embodiment enhances identity authentication security.
    Type: Application
    Filed: October 31, 2017
    Publication date: May 2, 2019
    Inventors: Zhenyu ZHONG, Tao WEI, Zhebin QIU