Patents by Inventor Junwei Zhu

Junwei Zhu 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: 11995144
    Abstract: The processing method comprises: acquiring a first image set corresponding to a product category; labelling at least one region of interest for each image in the first image set, wherein each region of interest is used for representing an object; acquiring a scanning window; using the scanning window to scan the regions of interest, acquiring scanning results, and placing the scanning results into a sample training set; establishing an illustration frame acquisition model by taking the first image set as input and taking the sample training set as output; acquiring an image to be processed, and using the illustration frame acquisition model to acquire a target webpage illustration frame corresponding to the image to be processed; and cutting, according to the target webpage illustration frame, the image to be processed so as to obtain a target webpage illustration.
    Type: Grant
    Filed: January 2, 2020
    Date of Patent: May 28, 2024
    Assignees: BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO. LTD., BEIJING JINGDONG CENTURY TRADING CO., LTD.
    Inventors: Xichen Wang, Zhentao Zhang, Zhidong She, Junwei Zhu, Gang Wang, Liang Zhang, Zhengfeng Rao
  • Publication number: 20240161465
    Abstract: An image processing method including obtaining a fake template sample group comprising a first source image, a real labeled image, and a fake template image, inputting the fake template image into an identity swapping model to obtain a first identity swapping image of the fake template image, obtaining a fake labeled sample group comprising a second source image, a real template image, and a fake labeled image, the fake labeled image being based on identity swapping processing of the real template image, inputting the real template image into the identity swapping model to obtain a second identity swapping image of the real template image, and training the identity swapping model based on the fake template sample group, the first identity swapping image, the fake labeled sample group, and the second identity swapping image to generate a trained identity swapping model.
    Type: Application
    Filed: January 18, 2024
    Publication date: May 16, 2024
    Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED.
    Inventors: Keke HE, Junwei ZHU, Ying TAI, Chengjie WANG
  • Publication number: 20240153041
    Abstract: This application discloses a method for generating an image processing model performed by a computer device. The method includes: performing training by using a first source image sample, a first template image sample, and a first standard synthesized image, to obtain a first parameter adjustment model, and combining the first parameter adjustment model and a first resolution update layer into a first update model; adjusting the first update model into a second parameter adjustment model using a second source image sample and a second template image sample and a second standard synthesized image; combining the second parameter adjustment model and a second resolution update layer into a second update model; and adjusting the second update model into a target image fusion model using a third source image sample, a third template image sample and a third standard synthesized image.
    Type: Application
    Filed: January 19, 2024
    Publication date: May 9, 2024
    Inventors: Keke HE, Junwei ZHU, Wenqing CHU, Ying TAI, Chengjie WANG
  • Publication number: 20240140699
    Abstract: The present invention discloses a container equipment for enclosed transportation and heterotopic and aerobic stabilization of reserved garbage, which includes a container body and a functional lining provided on an inner wall of the container body, wherein the functional lining is provided with a circulating air low-temperature evaporation system, a water distribution and drainage system and a heating and insulating system; the circulating air low-temperature evaporation system includes an air inlet manifold, an air distribution perforated pipe, a base plate water discharge and air distribution groove and a top plate water distribution and air guide groove, an air extraction perforated pipe, a fan, an air outlet pipe and a quicklime dehydration and deodorization system; the water distribution and drainage system includes a percolate feeding pipe, a fiber capillary water distribution pipe, the top plate water distribution and air guide groove, a side drain, a main drain and a percolate discharge pipe; the hea
    Type: Application
    Filed: April 28, 2022
    Publication date: May 2, 2024
    Inventors: Jun WU, Yifan CHEN, Zhouzhi PAN, YiIian LV, Haitao MA, Junwei ZHU, ZhiIi YANG, Pinghai Li, Wangfeng XUE
  • Publication number: 20240106891
    Abstract: Embodiments of this application provide a peer-to-peer network scheduling method. The method includes: obtaining a fragment file list, where the fragment file list includes information about a plurality of fragment files, each fragment file includes one or more segments, and each segment corresponds to one segment number; downloading a missing segment in a target fragment file from another client device based on a downloading progress of downloading each segment of the target fragment file by each client device; and when a player requests the target fragment file, stopping downloading the missing segment in the target fragment file from the another client device, and downloading the missing segment in the target fragment file from a CDN server. According to the embodiments of this application, a computation amount and resource consumption of a Tracker server can be reduced, and data transmission efficiency of a P2P network can be improved.
    Type: Application
    Filed: January 19, 2022
    Publication date: March 28, 2024
    Inventors: Jun JIANG, Junwei ZHU, Yongfang QIN, Nanling Zheng
  • Publication number: 20240106890
    Abstract: Embodiments of this application provides a peer-to-peer network scheduling method. The method includes: obtaining a fragment file list, where the fragment file list includes information about a plurality of fragment files, each fragment file includes one or more segments, and each segment corresponds to one segment number; downloading one or more target segments corresponding to one or more target segment numbers from a CDN server based on the fragment file list and the one or more target segment numbers, where the one or more target segment numbers are located in a target segment list; adjusting the target segment list based on information about data obtained from and/or sent to another client device, to obtain an adjusted target segment list; and downloading one or more target segments corresponding to one or more target segment numbers in the adjusted target segment list from the CDN server.
    Type: Application
    Filed: January 19, 2022
    Publication date: March 28, 2024
    Inventors: Jun JIANG, Junwei ZHU, Yongfang QIN
  • Patent number: 11935167
    Abstract: Disclosed in embodiments of the present disclosure are a method and apparatus for virtual fitting. A specific implementation of the method comprises: receiving a fitting request comprising a model picture and a user image; performing human body positioning and surface coordinate analysis on the model picture and the user image respectively; performing clothing segmentation on the model picture and the user image respectively; on the basis of the clothing segmentation result and the surface coordinate analysis result, covering the pixels corresponding to a piece of clothing in the model picture to corresponding positions in the user image to obtain a synthesized image and information to be completed; and inputting the synthesized image, the positioning result of the user image, and said information into a pre-trained image completion network to obtain a completed image.
    Type: Grant
    Filed: March 26, 2020
    Date of Patent: March 19, 2024
    Assignees: RELING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO., LTD., BEIJING JINGDONG CENTURY TRADING CO., LTD.
    Inventors: Junwei Zhu, Zhidong She, Zhentao Zhang
  • Patent number: 11863801
    Abstract: The present disclosure describes techniques for generating live streaming video data and playing live streaming video. The techniques comprise obtaining live broadcasting video data; identifying a target object in a video frame; determining a target area based on the target object in the video frame; encoding data indicative of the target area based on a predetermined format for supplementary enhancement information to obtain encoded target area data; and adding the encoded target area data to a data packet corresponding to the video frame, wherein the data packet is encoded based on a predetermined video data format, and wherein the predetermined video data format and the predetermined format for supplementary enhancement information are mutually compatible data encoding formats.
    Type: Grant
    Filed: August 3, 2021
    Date of Patent: January 2, 2024
    Assignee: SHANGHAI BILIBILI TECHNOLOGY CO., LTD.
    Inventors: Jun Jiang, Junwei Zhu, Yongfang Qin
  • Publication number: 20230394633
    Abstract: This application provides an image processing method and apparatus. The method includes acquiring an identity feature of a source image and an initial attribute feature of at least one measure of a target image in response to receiving a face change request; inputting the identity feature and the initial attribute feature of the at least one measure into a face change model; iteratively performing feature fusion on the identity feature and the initial attribute feature of the at least one measure by using the face change model to obtain a fusion feature; and generating a target face change image based on the fusion feature by using the face change model, and outputting the target face change image, a face in the target face change image being fused with an identity feature of the source face and a target attribute feature of the target face.
    Type: Application
    Filed: November 11, 2022
    Publication date: December 7, 2023
    Inventors: Yuchen LUO, Junwei ZHU, Keke HE, Wenqing CHU, Ying TAI, Chengjie WANG
  • Publication number: 20230316607
    Abstract: This application provides an image processing method performed by a computer device. The image processing method includes: receiving a face swapping request; acquiring an attribute parameter of the image, an attribute parameter of the target face, and a face feature of the target face, the attribute parameter of the image indicating a three-dimensional attribute of the face in the image; determining a target attribute parameter based on the attribute parameter of the image and the attribute parameter of the target face; determining a target comprehensive feature based on the target attribute parameter and the face feature of the target face; encoding the image to obtain an image encoding feature of the image; migrating the target comprehensive feature to the image encoding feature of the image by normalization to obtain a fusion encoding feature; and decoding the fusion encoding feature to obtain a target face-swapped image including a fusion face.
    Type: Application
    Filed: November 9, 2022
    Publication date: October 5, 2023
    Inventors: Keke HE, Junwei ZHU, Xinyi ZHANG, Ying TAI, Chengjie WANG
  • Publication number: 20230290128
    Abstract: An de-identification method includes: performing sampling on a target space of a projector in a target network model to obtain N virtual identity vectors, N being a positive integer; extracting, by using an attribute extractor in the target network model, M attribute vectors from a target image, M being a positive integer; and generating, by using a generator in the target network model, a de-identified image of the target image based on the N virtual identity vectors and the M attribute vectors.
    Type: Application
    Filed: December 6, 2022
    Publication date: September 14, 2023
    Inventors: Yuchen LUO, Junwei ZHU, Keke HE, Wenqing CHU, Ying TAI, Chengjie WANG
  • Publication number: 20230281833
    Abstract: A facial image processing method includes: obtaining first optical flow information; obtaining, based on the first optical flow information, second optical flow information through an optical flow information prediction sub-model of an image processing model; generating, based on the first facial sample image and the second optical flow information, a predicted image of the first facial sample image through a generator of the image processing model; discriminating the predicted image and the second facial sample image through a discriminator of the image processing model to obtain a first discrimination result and a second discrimination result; and training the image processing model based on the first discrimination result, the second discrimination result, the predicted image, the second facial sample image, the first optical flow information, and the second optical flow information.
    Type: Application
    Filed: May 10, 2023
    Publication date: September 7, 2023
    Inventors: Feida ZHU, Junwei ZHU, Yun CAO, Ying TAI, Chengjie WANG, Jilin LI
  • Publication number: 20230245351
    Abstract: Embodiments of this application disclose an image style conversion method performed by an electronic device. The method includes: performing quality enhancement on a first target style image to obtain a second target style image; performing feature extraction on the second target style image to obtain a target style feature; performing migration training on a preset target style conversion model by using a full style conversion model and the target style feature to obtain a target style conversion model; inputting a full style feature, the target style feature, and a to-be-converted image into the target style conversion model, and performing style conversion on the to-be-converted image using the target style conversion model to obtain a target image conforming to a target style.
    Type: Application
    Filed: March 29, 2023
    Publication date: August 3, 2023
    Inventors: Yun CAO, Xinyi ZHANG, Junwei ZHU, Ying TAI, Mu ZHANG, Chengjie WANG, Feiyue HUANG
  • Patent number: 11712043
    Abstract: Disclosed are Aspergillus oryzae aged cheese and a preparation method thereof, wherein the preparation method of the Aspergillus oryzae cheese comprises the following steps: (1) inoculating raw milk after sterilization with lactic acid bacteria fermentation agent and Aspergillus oryzae spore powder, fermenting to a pH value of 6.3-6.5, wherein an additive amount of the Aspergillus oryzae spore powder is 0.001‰-0.008‰‰ of a mass of the raw milk; (2) adding rennin and obtaining curd after curding; (3) cutting the curd to obtain curd blocks; and (4) moulding the curd blocks after expelling whey, and performing pickling and maturing after demoulding, wherein 1-7 days are taken for maturing under 20-30° C.; 7-15 days are taken for maturing under 15-20° C.; 10-20 days are taken for continuing maturing under 8-12° C.; and relative humidity of an environment for maturing is 85%-95%.
    Type: Grant
    Filed: July 2, 2014
    Date of Patent: August 1, 2023
    Assignee: BRIGHT DAIRY & FOOD CO., LTD
    Inventors: Jianping Hou, Benheng Guo, Zhenmin Liu, Huaning Yu, Feng Hang, Xin Song, Haibo Mu, Qinbo Wang, Junwei Zhu
  • Publication number: 20230098548
    Abstract: A computing device acquires an original image sequence. The device performs image preprocessing on the original image sequence to obtain a feature map sequence and a confidence map sequence that are corresponding to the original image sequence. The device performs feature fusion on the feature map sequence based on the confidence map sequence, to obtain a target fused feature map corresponding to a target original image frame in the original image sequence. The device reconstructs the target original image frame based on the target fused feature map to obtain a target reconstructed image frame. Credibility supervision at the pixel level is performed on features in the feature fusion process to guide the fusion of image features with high credibility, thereby improving the image quality of a reconstructed image.
    Type: Application
    Filed: November 28, 2022
    Publication date: March 30, 2023
    Inventors: Xinyi ZHANG, Junwei ZHU, Wenqing CHU, Ying TAI, Chengjie WANG, Jilin LI, Feiyue HUANG
  • Publication number: 20230100427
    Abstract: This application discloses a face image processing method performed by an electronic device. The method includes: acquiring a face image of a source face and a face template image of a template face; performing three-dimensional face modeling on the face image and the face template image to obtain a three-dimensional face image feature of the face image and a three-dimensional face template image feature of the face template image; fusing the three-dimensional face image feature and the three-dimensional face template image feature to obtain a three-dimensional fusion feature; performing face replacement feature extraction on the face image based on the face template image to obtain an initial face replacement feature; transforming the initial face replacement feature based on the three-dimensional fusion feature to obtain a target face replacement feature; and replacing the template face with the source face based on the target face replacement feature to obtain a target face image.
    Type: Application
    Filed: November 28, 2022
    Publication date: March 30, 2023
    Inventors: Keke HE, Junwei ZHU, Yandan ZHAO, Xu CHEN, Ying TAI, Chengjie WANG, Jilin LI, Feiyue HUANG
  • Publication number: 20230081982
    Abstract: An image processing method includes performing additional image feature extraction on a training source face image to obtain a source additional image feature, performing identity feature extraction on the training source face image to obtain a source identity feature, inputting a training template face image into an encoder in a to-be-trained face swapping model to obtain a face attribute feature, inputting the source additional image feature, the source identity feature, and the face attribute feature into a decoder in the face swapping model for decoding to obtain a decoded face image, obtaining a target model loss value based on an additional image difference between the decoded face image and a comparative face image, and adjusting the model parameters of the encoder and the decoder based on the target model loss value to obtain the trained face swapping model.
    Type: Application
    Filed: October 31, 2022
    Publication date: March 16, 2023
    Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Keke HE, Junwei ZHU, Hui NI, Yun CAO, Xu CHEN, Ying TAI, Chengjie WANG, Jilin LI, Feiyue HUANG
  • Patent number: 11595731
    Abstract: The present disclosure describes techniques of synchronizing subtitles in live broadcast The disclosed techniques comprise obtaining a source signal and a simultaneous interpretation signal in a live broadcast; performing voice recognition on the simultaneous interpretation signal in real-time to obtain corresponding translation text; delaying the simultaneous interpretation signal to obtain a first delayed signal; delaying the source signal to obtain a second delayed signal; obtaining proofreading results of the first delayed signal and the corresponding translation text; determining proofread subtitles based on the proofreading results; and sending the proofread subtitles and the second delay signal to a live display interface.
    Type: Grant
    Filed: February 5, 2021
    Date of Patent: February 28, 2023
    Assignee: SHANGHAI BILIBILI TECHNOLOGY CO., LTD.
    Inventors: Jun Jiang, Junwei Zhu, Zhaozhi Xiong, Nanling Zheng
  • Publication number: 20220245876
    Abstract: Disclosed in embodiments of the present disclosure are a method and apparatus for virtual fitting. A specific implementation of the method comprises: receiving a fitting request comprising a model picture and a user image; performing human body positioning and surface coordinate analysis on the model picture and the user image respectively; performing clothing segmentation on the model picture and the user image respectively; on the basis of the clothing segmentation result and the surface coordinate analysis result, covering the pixels corresponding to a piece of clothing in the model picture to corresponding positions in the user image to obtain a synthesized image and information to be completed; and inputting the synthesized image, the positioning result of the user image, and said information into a pre-trained image completion network to obtain a completed image.
    Type: Application
    Filed: March 26, 2020
    Publication date: August 4, 2022
    Inventors: Junwei ZHU, Zhidong SHE, Zhentao ZHANG
  • Publication number: 20220046291
    Abstract: The present disclosure describes techniques for generating live streaming video data and playing live streaming video. The techniques comprise obtaining live broadcasting video data; identifying a target object in a video frame; determining a target area based on the target object in the video frame; encoding data indicative of the target area based on a predetermined format for supplementary enhancement information to obtain encoded target area data; and adding the encoded target area data to a data packet corresponding to the video frame, wherein the data packet is encoded based on a predetermined video data format, and wherein the predetermined video data format and the predetermined format for supplementary enhancement information are mutually compatible data encoding formats.
    Type: Application
    Filed: August 3, 2021
    Publication date: February 10, 2022
    Inventors: Jun JIANG, Junwei Zhu, Yongfang Qin