Patents by Inventor Hu YE

Hu YE 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).

  • Publication number: 20260278887
    Abstract: Embodiments of this application disclose an image generation method by an electronic device. The method includes: acquiring a source image, a noise image, and a preset posture image, the noise image being different from the source image; extracting a source posture image from the source image; fusing at least the source image, the noise image, the preset posture image, and the source posture image to obtain a target image; inputting the source image to an image feature extractor in an image generation model to extract a source image comprehensive feature; and inputting the target image and the source image comprehensive feature to an image denoiser in the image generation model to obtain an object image, the object image representing an image of an object in the source image in a preset posture.
    Type: Application
    Filed: May 7, 2026
    Publication date: September 17, 2026
    Inventor: Hu YE
  • Publication number: 20260278858
    Abstract: Provided are a data processing method and apparatus, a device, a medium and a product. The method includes: first, obtaining at least one piece of data; then, for any piece of data of the at least one piece of data, obtaining, from a dictionary of a target model, a discrete feature matching an index determination result of the piece of data, such that the discrete feature may represent information carried by the piece of data; and then, performing, by using the target model, prediction processing on the discrete feature, to obtain an index prediction result, such that the index prediction result is used to indicate a usage probability of each index in an index sequence of the dictionary, and an index with a largest usage probability indicated by the index prediction result is an index corresponding to a certain text or an index corresponding to a certain image.
    Type: Application
    Filed: March 13, 2026
    Publication date: September 17, 2026
    Inventors: Huichao ZHANG, Li'ao QU, Yiheng LIU, Xu WANG, Yi JIANG, Hu YE, Yiming GAO, Kang DU, Xinglong WU
  • Patent number: 12737045
    Abstract: Provided is a method for processing an electroencephalogram signal executed by a computer device. The method includes acquiring an electroencephalogram signal, the electroencephalogram signal comprising an electroencephalogram signal data segment of a specified duration; determining a plurality of time nodes in the electroencephalogram signal data segment according to a preset time interval; predicting an action intention corresponding to each time node based on the electroencephalogram signal data segment to obtain action intention prediction results respectively corresponding to the plurality of time nodes; and determining a target action intention according to the action intention prediction results.
    Type: Grant
    Filed: March 27, 2025
    Date of Patent: September 15, 2026
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Yanning Zhou, Kaiwen Xiao, Tian Shen, Jingwen Ye, Hu Ye, Ziyuan Wang, Sibo Liu, Yiqin Zhu, Xiao Han
  • Publication number: 20260268138
    Abstract: An artificial intelligence-based text-to-image generation model training method, apparatus, and computer-readable storage medium for cross-modal learning. The method obtains sample images and extracts first image features from them. These first image features are aligned into a text feature space to obtain second image features representing the sample images in text-aligned form. Images are generated based on these second image features to produce prediction results. A text-to-image generation model is trained using these prediction results, enabling the model to learn cross-modal relationships between text and image domains through feature space alignment, facilitating effective text-to-image generation capabilities.
    Type: Application
    Filed: April 28, 2026
    Publication date: September 10, 2026
    Applicant: Tencent Technology (Shenzhen) Company Limited
    Inventors: Sibo LIU, Hu YE, Jun ZHANG
  • Publication number: 20260179177
    Abstract: This application relates to a video frame interpolation method performed by a computer device. The method includes: determining first optical flow information between two video frame images; predicting an intermediate frame image between the two video frame images based on the first optical flow information; for each of the two video frame images, determining second optical flow information between the video frame image and the predicted intermediate frame image; selecting image blocks corresponding to the first pixel points from the video frame image according to the second optical flow information; updating pixel values at first pixel points in the predicted intermediate frame image based on image blocks corresponding to the first pixel points in the predicted intermediate frame image; and fusing updated intermediate frame images respectively corresponding to the two video frame images to obtain a fused intermediate frame image.
    Type: Application
    Filed: February 12, 2026
    Publication date: June 25, 2026
    Inventor: Hu YE
  • Publication number: 20260154942
    Abstract: The present application discloses a data processing method and apparatus, device, medium and product, where the method includes: acquiring a target image, a semantic-level feature of the target image, a pixel-level feature of the target image, a semantic-level codebook, and a pixel-level codebook, where a plurality of indices are shared between the semantic-level codebook and the pixel-level codebook, and different indices indicate different entries in the same codebook; summing, for any of the indices, a distance between an entry indicated by the index in the semantic-level codebook and the semantic-level feature and a distance between an entry indicated by the index in the pixel-level codebook and the pixel-level feature to obtain a distance sum corresponding to the index; and comparing the distance sums corresponding to the indices to obtain a minimum value, and determining an indexed result of the target image according to an index corresponding to the minimum value.
    Type: Application
    Filed: November 28, 2025
    Publication date: June 4, 2026
    Inventors: Li'ao Qu, Huichao Zhang, Yiheng Liu, Xu Wang, Yi Jiang, Yiming Gao, Hu Ye, Kang Du, Zehuan Yuan, Xinglong Wu
  • Publication number: 20260154860
    Abstract: The present application discloses an image generation method and apparatus, a device, a medium and a product. The method includes a process of predicting a token sequence under a plurality of scales, and the process of predicting a token sequence under each scale is obtained through multiple rounds of sampling prediction, so as to realize a later round of sampling prediction on the basis of a result obtained from an earlier round of sampling prediction under the same scale so that the later round of sampling prediction may acquire an associated relationship between different local areas (for example, different local areas represented by different tokens) from the result.
    Type: Application
    Filed: November 26, 2025
    Publication date: June 4, 2026
    Inventors: li’ao QU, Huichao ZHANG, Yiheng LIU, Xu WANG, Yi JIANG, Yiming GAO, Hu YE, Kang DU, Zehuan YUAN, Xinglong WU
  • Publication number: 20250224805
    Abstract: Provided is a method for processing an electroencephalogram signal executed by a computer device. The method includes acquiring an electroencephalogram signal, the electroencephalogram signal comprising an electroencephalogram signal data segment of a specified duration; determining a plurality of time nodes in the electroencephalogram signal data segment according to a preset time interval; predicting an action intention corresponding to each time node based on the electroencephalogram signal data segment to obtain action intention prediction results respectively corresponding to the plurality of time nodes; and determining a target action intention according to the action intention prediction results.
    Type: Application
    Filed: March 27, 2025
    Publication date: July 10, 2025
    Inventors: Yanning ZHOU, Kaiwen XIAO, Tian SHEN, Jingwen YE, Hu YE, Ziyuan WANG, Sibo LIU, Yiqin ZHU, Xiao HAN
  • Patent number: 12223645
    Abstract: Methods, apparatus, device, and storage medium for identifying an abnormal cell in a to-be-detected sample are disclosed. The method includes obtaining, by a device, multi-layer images of a to-be-detected sample, the to-be-detected sample comprising a single cell and a cell cluster; obtaining, by the device, multi-layer image blocks of the single cell and multi-layer image blocks of the cell cluster according to the multi-layer images; obtaining, by the device, a first identification result by a first image identification network according to the multi-layer image blocks of the single cell; obtaining, by the device, a second identification result by a second image identification network according to the multi-layer image blocks of the cell cluster; and determining, by the device, whether an abnormal cell exists in the to-be-detected sample according to the first identification result and the second identification result.
    Type: Grant
    Filed: March 23, 2022
    Date of Patent: February 11, 2025
    Assignee: Tencent Technology (Shenzhen) Company Limited
    Inventors: De Cai, Hu Ye, Zhaoxuan Ma, Xiao Han
  • Patent number: 12046056
    Abstract: A computer device obtains a to-be-annotated image having a first magnification. The device obtains an annotated image from an annotated image set, the annotated image distinct from the to-be-annotated image and having a second magnification that is distinct from with the first magnification. The annotated image set includes at least one annotated image. The device matches the to-be-annotated image with the annotated image to obtain an affine transformation matrix, and generates annotation information of the to-be-annotated image according to the affine transformation matrix and the annotated image. In this way, annotations corresponding to images at different magnifications may be migrated. For example, the annotations may be migrated from the low-magnification images to the high-magnification images, thereby reducing the manual annotation amount and avoiding repeated annotations, and further improving annotation efficiency and reducing labor costs.
    Type: Grant
    Filed: July 19, 2021
    Date of Patent: July 23, 2024
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Hu Ye, Xiao Han, Kaiwen Xiao, Niyun Zhou, Mingyang Chen
  • Patent number: 11995827
    Abstract: An image display method includes: processing a first image to obtain a first feature image, the first image being an image of a local area of a smear captured by a microscope, and the local area including multiple objects to be tested; obtaining a second feature image corresponding to the first feature image, the second feature image and the first feature image having a same size; obtaining a third feature image according to an image obtained by overlaying the first feature image and the second feature image, a feature point in the third feature image indicating a possibility that one of the multiple objects is an abnormal object; obtaining a second image according to the third feature image; and displaying the second image superimposed on the first image.
    Type: Grant
    Filed: April 11, 2022
    Date of Patent: May 28, 2024
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Zhaoxuan Ma, De Cai, Hu Ye, Xiao Han, Yanqing Kong, Hongping Tang
  • Patent number: 11954852
    Abstract: This application describes a medical image classification method, a model training method, and a server. The medical image classification method includes: obtaining, by a device, a medical image data set. The device includes a memory storing instructions and a processor in communication with the memory. The method includes performing, by the device, quality analysis on the medical image data set, to extract feature information of a medical image in the medical image data set; and classifying, by the device, the medical image data set based on the feature information and by using a pre-trained deep learning network for performing anomaly detection and classification, to obtain a classification result.
    Type: Grant
    Filed: July 14, 2021
    Date of Patent: April 9, 2024
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Kaiwen Xiao, Xiao Han, Hu Ye, Niyun Zhou
  • Publication number: 20220237790
    Abstract: An image display method includes: processing a first image to obtain a first feature image, the first image being an image of a local area of a smear captured by a microscope, and the local area including multiple objects to be tested; obtaining a second feature image corresponding to the first feature image, the second feature image and the first feature image having a same size; obtaining a third feature image according to an image obtained by overlaying the first feature image and the second feature image, a feature point in the third feature image indicating a possibility that one of the multiple objects is an abnormal object; obtaining a second image according to the third feature image; and displaying the second image superimposed on the first image.
    Type: Application
    Filed: April 11, 2022
    Publication date: July 28, 2022
    Inventors: Zhaoxuan MA, De CAI, Hu YE, Xiao HAN, Yanqing KONG, Hongping TANG
  • Publication number: 20220215548
    Abstract: Methods, apparatus, device, and storage medium for identifying an abnormal cell in a to-be-detected sample are disclosed. The method includes obtaining, by a device, multi-layer images of a to-be-detected sample, the to-be-detected sample comprising a single cell and a cell cluster; obtaining, by the device, multi-layer image blocks of the single cell and multi-layer image blocks of the cell cluster according to the multi-layer images; obtaining, by the device, a first identification result by a first image identification network according to the multi-layer image blocks of the single cell; obtaining, by the device, a second identification result by a second image identification network according to the multi-layer image blocks of the cell cluster; and determining, by the device, whether an abnormal cell exists in the to-be-detected sample according to the first identification result and the second identification result.
    Type: Application
    Filed: March 23, 2022
    Publication date: July 7, 2022
    Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: De CAI, Hu YE, Zhaoxuan MA, Xiao HAN
  • Publication number: 20210350169
    Abstract: A computer device obtains a to-be-annotated image having a first magnification. The device obtains an annotated image from an annotated image set, the annotated image distinct from the to-be-annotated image and having a second magnification that is distinct from with the first magnification. The annotated image set includes at least one annotated image. The device matches the to-be-annotated image with the annotated image to obtain an affine transformation matrix, and generates annotation information of the to-be-annotated image according to the affine transformation matrix and the annotated image. In this way, annotations corresponding to images at different magnifications may be migrated. For example, the annotations may be migrated from the low-magnification images to the high-magnification images, thereby reducing the manual annotation amount and avoiding repeated annotations, and further improving annotation efficiency and reducing labor costs.
    Type: Application
    Filed: July 19, 2021
    Publication date: November 11, 2021
    Inventors: Hu YE, Xiao HAN, Kaiwen XIAO, Niyun ZHOU, Mingyang CHEN
  • Publication number: 20210343012
    Abstract: This application describes a medical image classification method, a model training method, and a server. The medical image classification method includes: obtaining, by a device, a medical image data set. The device includes a memory storing instructions and a processor in communication with the memory. The method includes performing, by the device, quality analysis on the medical image data set, to extract feature information of a medical image in the medical image data set; and classifying, by the device, the medical image data set based on the feature information and by using a pre-trained deep learning network for performing anomaly detection and classification, to obtain a classification result.
    Type: Application
    Filed: July 14, 2021
    Publication date: November 4, 2021
    Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Kaiwen XIAO, Xiao HAN, Hu YE, Niyun ZHOU