Patents by Inventor YINGLAN A

YINGLAN A 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: 12165284
    Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a dual-branched neural network architecture to harmonize composite images. For example, in one or more implementations, the transformer-based harmonization system uses a convolutional branch and a transformer branch to generate a harmonized composite image based on an input composite image and a corresponding segmentation mask. More particularly, the convolutional branch comprises a series of convolutional neural network layers followed by a style normalization layer to extract localized information from the input composite image. Further, the transformer branch comprises a series of transformer neural network layers to extract global information based on different resolutions of the input composite image.
    Type: Grant
    Filed: March 21, 2022
    Date of Patent: December 10, 2024
    Assignee: Adobe Inc.
    Inventors: He Zhang, Jianming Zhang, Jose Ignacio Echevarria Vallespi, Kalyan Sunkavalli, Meredith Payne Stotzner, Yinglan Ma, Zhe Lin, Elya Shechtman, Frederick Mandia
  • Patent number: 12148074
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating harmonized digital images utilizing an object-to-object harmonization neural network. For example, the disclosed systems implement, and learn parameters for, an object-to-object harmonization neural network to combine a style code from a reference object with features extracted from a target object. Indeed, the disclosed systems extract a style code from a reference object utilizing a style encoder neural network. In addition, the disclosed systems generate a harmonized target object by applying the style code of the reference object to a target object utilizing an object-to-object harmonization neural network.
    Type: Grant
    Filed: October 18, 2021
    Date of Patent: November 19, 2024
    Assignee: Adobe Inc.
    Inventors: He Zhang, Jeya Maria Jose Valanarasu, Jianming Zhang, Jose Ignacio Echevarria Vallespi, Kalyan Sunkavalli, Yilin Wang, Yinglan Ma, Zhe Lin, Zijun Wei
  • Patent number: 11978190
    Abstract: A rapid detection system for water and impurity of machine-harvested seed cotton in purchase link, including: a seed cotton large-impurity-cleaning device, a seed cotton sample case, a driving and transmission device, a cotton pressing device, an image collection and processing device, and a moisture regain rate detection device and a control cabinet. The seed cotton sample case consists of a positioning plate and a high light transmittance glass case, the weighing device consists of a weighing sensor, a pallet, and an electric push rod. The driving and transmission device consists of the rollers, the motor of conveyor belts and conveyor belts, the cotton pressing device consists of an electric push rod, a connecting rod, a connecting plate, and a high light transmittance glass plate. Said rapid detection system could realize the rapid detection to the impurity rate and moisture regain rate of the seed cotton.
    Type: Grant
    Filed: August 24, 2021
    Date of Patent: May 7, 2024
    Assignee: Shihezi University
    Inventors: Ruoyu Zhang, Long Wan, Yinglan Jiang, Mengyun Zhang, Jinqiang Chang, Fangdan Song
  • Publication number: 20230298148
    Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a dual-branched neural network architecture to harmonize composite images. For example, in one or more implementations, the transformer-based harmonization system uses a convolutional branch and a transformer branch to generate a harmonized composite image based on an input composite image and a corresponding segmentation mask. More particularly, the convolutional branch comprises a series of convolutional neural network layers followed by a style normalization layer to extract localized information from the input composite image. Further, the transformer branch comprises a series of transformer neural network layers to extract global information based on different resolutions of the input composite image.
    Type: Application
    Filed: March 21, 2022
    Publication date: September 21, 2023
    Inventors: He Zhang, Jianming Zhang, Jose Ignacio Echevarria Vallespi, Kalyan Sunkavalli, Meredith Payne Stotzner, Yinglan Ma, Zhe Lin, Elya Shechtman, Frederick Mandia
  • Publication number: 20230122623
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating harmonized digital images utilizing an object-to-object harmonization neural network. For example, the disclosed systems implement, and learn parameters for, an object-to-object harmonization neural network to combine a style code from a reference object with features extracted from a target object. Indeed, the disclosed systems extract a style code from a reference object utilizing a style encoder neural network. In addition, the disclosed systems generate a harmonized target object by applying the style code of the reference object to a target object utilizing an object-to-object harmonization neural network.
    Type: Application
    Filed: October 18, 2021
    Publication date: April 20, 2023
    Inventors: He Zhang, Jeya Maria Jose Valanarasu, Jianming Zhang, Jose Ignacio Echevarria Vallespi, Kalyan Sunkavalli, Yilin Wang, Yinglan Ma, Zhe Lin, Zijun Wei
  • Patent number: 11307881
    Abstract: In implementations of systems for generating suggestions with knowledge graph embedding vectors, a computing device implements a suggestion system to receive input data describing user interactions with an application for editing digital content. The suggestion system generates input embedding vectors based on the user interactions with the application and determines an item based on the input embedding vectors and knowledge graph embedding vectors generated from nodes of a knowledge graph describing a tutorial for editing digital content. The suggestion system generates an indication of the item for display in a user interface of a display device.
    Type: Grant
    Filed: November 11, 2020
    Date of Patent: April 19, 2022
    Assignee: Adobe Inc.
    Inventors: Ripul Bhutani, Oliver Markus Michael Brdiczka, Doo Soon Kim, Aliakbar Darabi, Yinglan Ma
  • Publication number: 20220067912
    Abstract: Disclosed is a rapid detection system for water and impurity of machine-harvested seed cotton in purchase link, including: a seed cotton large-impurity-cleaning device, a seed cotton sample case, a driving and transmission device, a cotton pressing device, an image collection and processing device, a moisture regain rate detection device and a control cabinet; the seed cotton sample case consists of a positioning plate and a high light transmittance glass case, the weighing device consists of a weighing sensor, a pallet, and an electric push rod; the driving and transmission device consists of the rollers, the motor of conveyor belts and conveyor belts, the cotton pressing device consists of an electric push rod, a connecting rod, a connecting plate, and a high light transmittance glass plate. Said rapid detection system could realize the rapid detection to the impurity rate and moisture regain rate of the seed cotton.
    Type: Application
    Filed: August 24, 2021
    Publication date: March 3, 2022
    Inventors: Ruoyu ZHANG, Long WAN, Yinglan JIANG, Mengyun ZHANG, Jinqiang CHANG, Fangdan SONG
  • Patent number: 11257491
    Abstract: This application relates generally to modifying visual data based on audio commands and more specifically, to performing complex operations that modify visual data based on one or more audio commands. In some embodiments, a computer system may receive an audio input and identify an audio command based on the audio input. The audio command may be mapped to one or more operations capable of being performed by a multimedia editing application. The computer system may perform the one or more operations to edit to received multimedia data.
    Type: Grant
    Filed: November 29, 2018
    Date of Patent: February 22, 2022
    Assignee: ADOBE INC.
    Inventors: Sarah Kong, Yinglan Ma, Hyunghwan Byun, Chih-Yao Hsieh
  • Patent number: 11100917
    Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that generate ground truth annotations of target utterances in digital image editing dialogues in order to create a state-driven training data set. In particular, in one or more embodiments, the disclosed systems utilize machine and user defined tags, machine learning model predictions, and user input to generate a ground truth annotation that includes frame information in addition to intent, attribute, object, and/or location information. In at least one embodiment, the disclosed systems generate ground truth annotations in conformance with an annotation ontology that results in fast and accurate digital image editing dialogue annotation.
    Type: Grant
    Filed: March 27, 2019
    Date of Patent: August 24, 2021
    Assignee: ADOBE INC.
    Inventors: Trung Bui, Zahra Rahimi, Yinglan Ma, Seokhwan Kim, Franck Dernoncourt
  • Publication number: 20200312298
    Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that generate ground truth annotations of target utterances in digital image editing dialogues in order to create a state-driven training data set. In particular, in one or more embodiments, the disclosed systems utilize machine and user defined tags, machine learning model predictions, and user input to generate a ground truth annotation that includes frame information in addition to intent, attribute, object, and/or location information. In at least one embodiment, the disclosed systems generate ground truth annotations in conformance with an annotation ontology that results in fast and accurate digital image editing dialogue annotation.
    Type: Application
    Filed: March 27, 2019
    Publication date: October 1, 2020
    Inventors: Trung Bui, Zahra Rahimi, Yinglan Ma, Seokhwan Kim, Franck Dernoncourt
  • Patent number: 10706512
    Abstract: Methods and systems are provided for adjusting the brightness of images. In some implementations, an exposure bracketed set of input images produced by a camera is received. A brightness adjustment is determined for at least one input image from the set of input images. The determined brightness adjustment is applied to the input image. An output image is produced by exposure fusion from the set of input images, using the input image having the determined brightness adjustment. The output image is transmitted where, the transmitting causes display of the output image on a user device.
    Type: Grant
    Filed: March 7, 2017
    Date of Patent: July 7, 2020
    Assignee: ADOBE INC.
    Inventors: Yinglan Ma, Sylvain Philippe Paris, Chih-Yao Hsieh
  • Publication number: 20200175975
    Abstract: This application relates generally to modifying visual data based on audio commands and more specifically, to performing complex operations that modify visual data based on one or more audio commands. In some embodiments, a computer system may receive an audio input and identify an audio command based on the audio input. The audio command may be mapped to one or more operations capable of being performed by a multimedia editing application. The computer system may perform the one or more operations to edit to received multimedia data.
    Type: Application
    Filed: November 29, 2018
    Publication date: June 4, 2020
    Inventors: Sarah Kong, Yinglan Ma, Hyunghwan Byun, Chih-Yao Hsieh
  • Patent number: 10663445
    Abstract: The present disclosure provides a method and system for identifying plant species based on hyperspectral data, wherein the method includes: performing atmospheric radiation correction for the hyperspectral data of plants to be identified adopting Linear Regression method, to obtain corrected hyperspectral data, wherein, the hyperspectral data of the plants to be identified are collected by a hyperspectral ground object spectrometer provided within an unmanned aerial vehicle (UAV); performing external parameter orthogonalisation (EPO) processing for the corrected hyperspectral data; performing first order differential processing for the EPO processed hyperspectral data, to obtain hyperspectral data highlighting absorption peak information; performing discrete wavelet transformation processing for the hyperspectral data highlighting the absorption peak information, to obtain wavelet coefficients corresponding to the plants to be identified.
    Type: Grant
    Filed: May 6, 2018
    Date of Patent: May 26, 2020
    Inventors: Guoqiang Wang, Puze Wang, Yanbo Peng, Ruimin Li, Tingxi Liu, Wei Wang, Yinglan A
  • Publication number: 20190339242
    Abstract: The present disclosure provides a method and system for identifying plant species based on hyperspectral data, wherein the method includes: performing atmospheric radiation correction for the hyperspectral data of plants to be identified adopting Linear Regression method, to obtain corrected hyperspectral data, wherein, the hyperspectral data of the plants to be identified are collected by a hyperspectral ground object spectrometer provided within an unmanned aerial vehicle (UAV); performing external parameter orthogonalisation (EPO) processing for the corrected hyperspectral data; performing first order differential processing for the EPO processed hyperspectral data, to obtain hyperspectral data highlighting absorption peak information; performing discrete wavelet transformation processing for the hyperspectral data highlighting the absorption peak information, to obtain wavelet coefficients corresponding to the plants to be identified.
    Type: Application
    Filed: May 6, 2018
    Publication date: November 7, 2019
    Inventors: GUOQIANG WANG, PUZE WANG, YANBO PENG, RUIMIN LI, TINGXI LIU, WEI WANG, YINGLAN A
  • Publication number: 20180260941
    Abstract: Methods and systems are provided for adjusting the brightness of images. In some implementations, an exposure bracketed set of input images produced by a camera is received. A brightness adjustment is determined for at least one input image from the set of input images. The determined brightness adjustment is applied to the input image. An output image is produced by exposure fusion from the set of input images, using the input image having the determined brightness adjustment. The output image is transmitted where, the transmitting causes display of the output image on a user device.
    Type: Application
    Filed: March 7, 2017
    Publication date: September 13, 2018
    Inventors: YINGLAN MA, Sylvain Philippe PARIS, Chih-Yao HSIEH
  • Publication number: 20170239259
    Abstract: The present invention relates to a compound inhibiting HF-1 activity, a preparation method of the same, and a pharmaceutical composition comprising the same as an active ingredient. The compound of the present invention demonstrates anticancer activity not by non-selective cytotoxicity but by inhibiting the activity of HIF-1, the transcription factor playing an important role in cancer cell growth and metastasis. Accordingly, the compound or the pharmaceutically acceptable salt thereof according to the present invention inhibits HIF-1 activity, and therefore can be used as a therapeutic agent for solid tumors such as colon cancer, liver cancer, stomach cancer and breast cancer. In addition, the compound or the pharmaceutically acceptable salt thereof according to the present invention can be used as an active ingredient for a therapeutic agent for diabetic retinopathy or arthritis which may become worse when hypoxia-induced VEGF expression by HIF-1 increases.
    Type: Application
    Filed: December 12, 2014
    Publication date: August 24, 2017
    Applicants: KOREA RESEARCH INSTITUTE OF BIOSCIENCE AND BIOTECHNOLOGY, DONGGUK UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION
    Inventors: Kyeong LEE, Mi Sun WON, Hwan Mook KIM, Song Kyu PARK, Kiho LEE, Ki Hoon LEE, Chang Woo LEE, Jung Joon LEE, Kyung Sook CHUNG, Bo Kyung KIM, Yinglan JIN, Seung-hee LEE
  • Patent number: 8940936
    Abstract: The present invention relates to a compound inhibiting HF-1 activity, a preparation method of the same, and a pharmaceutical composition comprising the same as an active ingredient. The compound of the present invention demonstrates anticancer activity not by non-selective cytotoxicity but by inhibiting the activity of HIF-1, the transcription factor playing an important role in cancer cell growth and metastasis. Accordingly, the compound or the pharmaceutically acceptable salt thereof according to the present invention inhibits HIF-1 activity, and therefore can be used as a therapeutic agent for solid tumors such as colon cancer, liver cancer, stomach cancer and breast cancer. In addition, the compound or the pharmaceutically acceptable salt thereof according to the present invention can be used as an active ingredient for a therapeutic agent for diabetic retinopathy or arthritis which may become worse when hypoxia-induced VEGF expression by HIF-1 increases.
    Type: Grant
    Filed: October 17, 2011
    Date of Patent: January 27, 2015
    Assignees: Korea Research Institute of Bioscience and Biotechnology, Dongguk University Industry-Academic Cooperation Foundation
    Inventors: Kyeong Lee, Mi Sun Won, Hwan Mook Kim, Song Kyu Park, Kiho Lee, Ki Hoon Lee, Chang Woo Lee, Jung Joon Lee, Kyung Sook Chung, Bo Kyung Kim, Yinglan Jin, Seung-hee Lee
  • Patent number: 8887234
    Abstract: The present invention provides a method for network service selection and authentication in an IPv6 access network, a scheme for stateless auto-configuration and devices thereof. A NSP Information option containing the IPv6 address of a NSP edge router and a NSP name is defined in RA messages. A NSSA Information option is defined in RS option fields. The present invention enables IPv6 stateless auto-configuration in an access network. The new NSP Information option, the way of “one time authentication per subscriber network per NSP” and the use of IPv6 routing header promote the efficiency of IPv6 stateless auto-configuration and reduce the NSP selection and authentication traffic. The present invention provides an efficient solution for network service selection and authentication without introducing any other message exchange between terminals and access nodes.
    Type: Grant
    Filed: September 15, 2005
    Date of Patent: November 11, 2014
    Assignee: Alcatel Lucent
    Inventors: HaiBo Wen, RenXiang Yan, KeYao Zhu, YingLan Jiang, XuDong Zhu, FanXiang Bin, QingShan Zhang
  • Patent number: 8879418
    Abstract: Disclosed is a method for updating DNS of host in IPv6 stateless address auto-configuration, wherein an option is added in the RS message sent by a host and/or RA message sent by a router, said option including information for negotiation of updating DNS of host. Based on said information, the host negotiates with the router to determine whether the host or the router register, the mapping between the global address of the host and the full domain name of the host, to a DNS server, to complete updating the DNS of the host. This invention enables the host to correctly identify the matching relation between domain name suffix information and address prefix, and achieves the negotiation of updating DNS domain name between the host and the router. Since DNS updating is performed by a router instead of the host, the DNS updating would become simple and safe.
    Type: Grant
    Filed: December 20, 2005
    Date of Patent: November 4, 2014
    Assignee: Alcatel Lucent
    Inventors: Renxiang Yan, Yinglan Jiang, Qingshan Zhang, Fanxiang Bin
  • Patent number: 8655990
    Abstract: The present invention relates to an IPv6-based access device, edge router and method for stainless address configuration for IPv6 user equipment in an Ethernet access network, wherein, the access device adds the relay agent ID indicating the access device itself and the relevant port identifier indicating the user equipment to a router solicitation message sent by the user equipment in the form of a newly defined option, and forwards the message to the relevant edge router; and the edge router configures a dedicated address prefix for the user equipment according to the relay agent ID and port identifier, combines the address prefix, the relay ID and the port identifier into a router response message, and sends the response message to the relevant access equipment indicated by the relay ID; the access device sends a router advertisement message only including the address prefix via the line port indicated by the port identifier to user equipment.
    Type: Grant
    Filed: May 19, 2006
    Date of Patent: February 18, 2014
    Assignee: Alcatel Lucent
    Inventors: Keyao Zhu, Haibo Wen, Renxiang Yan, Yinglan Jiang, Fanxiang Bin, Qingshan Zhang