公开(公告)号：US20240249555A1

公开(公告)日：2024-07-25

申请号：US17995743

申请日：2022-04-20

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Song Xue ,  Yuan Feng ,  Ying Xin ,  Bin Zhang ,  Chao Li ,  Xiaodi Wang ,  Yunhao Wang ,  Yi Gu ,  Xiang Long ,  Honghui Zheng ,  Yan Peng ,  Zhuang Jia ,  Shumin Han

IPC: G06V40/20 ,  G06T7/73 ,  G06V10/25

CPC classification number: G06V40/20 ,  G06T7/73 ,  G06V10/25 ,  G06T2207/30196

Abstract: A method for detecting a human behavior includes: obtaining an image to be detected; obtaining a plurality of key points and a plurality of pieces of position information respectively corresponding to the plurality of key points by key-point recognition on the image to be detected; grouping the plurality of key points based on the plurality of pieces of position information to obtain a plurality of key-point groups, the plurality of key-point groups at least including a part of the plurality of key points; and determining a target human behavior based on key points in the plurality of key-point groups.

公开(公告)号：US20240037911A1

公开(公告)日：2024-02-01

申请号：US18109522

申请日：2023-02-14

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Ying Xin ,  Song Xue ,  Yuan Feng ,  Chao Li ,  Bin Zhang ,  Yunhao Wang ,  Shumin Han

IPC: G06V10/764 ,  G06V10/44 ,  G06V10/80 ,  G06V10/82

CPC classification number: G06V10/764 ,  G06V10/44 ,  G06V10/806 ,  G06V10/82

Abstract: Provided is an image classification method, an electronic device and a storage medium, relating to a field of artificial intelligence technology, and specifically, to the technical fields of deep learning, image processing and computer vision, which may be applied to scenes such as image classification. The image classification method includes: extracting a first image feature of a target image by using a first network model, where the first network model includes a convolutional neural network module; extracting a second image feature of the target image by using a second network model, where the second network model includes a deep self-attention transformer network (Transformer) module; fusing the first image feature and the second image feature to obtain a target feature to be recognized; and classifying the target image based on the target feature to be recognized.

公开(公告)号：US20230154163A1

公开(公告)日：2023-05-18

申请号：US18151108

申请日：2023-01-06

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Zhuang Jia ,  Xiang Long ,  Yan Peng ,  Honghui Zheng ,  Bin Zhang ,  Yunhao Wang ,  Ying Xin ,  Chao Li ,  Xiaodi Wang ,  Song Xue ,  Yuan Feng ,  Shumin Han

IPC: G06V10/774 ,  G06V10/58 ,  G06V10/764 ,  G06V10/776 ,  G06V20/70 ,  G06V10/77

CPC classification number: G06V10/774 ,  G06V10/58 ,  G06V10/764 ,  G06V10/776 ,  G06V20/70 ,  G06V10/7715

Abstract: A method for recognizing a category of an image includes: acquiring a spectral image; training an image recognition model based on the spectral image, in which the image recognition model acquires a spectral semantic feature of each pixel, a minimum distance between each pixel and each category, and a spectral distance between a first spectrum of each pixel and a second spectrum of each category; splices them; and performs classification and recognition based on the spliced feature to output a recognition probability of each pixel under each category; determining a loss function of the image recognition model, adjusting the image recognition model based on the loss function, and returning to training the adjusted image recognition model based on the spectral image until training ends; recognizing a maximum recognition probability, output from a target image recognition model, and using a category corresponding to the maximum recognition probability as a target category.