公开(公告)号：US20220360796A1

公开(公告)日：2022-11-10

申请号：US17870660

申请日：2022-07-21

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

Inventor： Desen ZHOU ,  Jian Wang ,  Hao Sun

IPC: H04N19/172 ,  H04N19/132

Abstract: A method and apparatus for recognizing an action. The method includes: acquiring a target video; determining action categories corresponding to the target video; determining, for each action category, a pre-action-conversion video frame and post-action-conversion video frame corresponding to the action category from the target video; and determining a number of actions corresponding to the each action category based on the pre-action-conversion video frame and post-action-conversion video frame corresponding to the each action category.

公开(公告)号：US11893708B2

公开(公告)日：2024-02-06

申请号：US17505889

申请日：2021-10-20

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

Inventor： Jian Wang ,  Xiang Long ,  Hao Sun ,  Zhiyong Jin ,  Errui Ding

IPC: G06K9/00 ,  G06T3/40 ,  G06F18/213 ,  G06F18/25 ,  G06N3/045

CPC classification number: G06T3/4046 ,  G06F18/213 ,  G06F18/253 ,  G06N3/045

Abstract: Provided are an image processing method and apparatus, a device, and a storage medium, relating to the technical field of image processing, in particular to the artificial intelligence fields such as computer vision and deep learning. The specific implementation scheme is as follows: inputting a to-be-processed image into an encoding network to obtain a basic image feature, wherein the encoding network includes at least two cascaded overlapping encoding sub-networks which perform encoding and fusion processing on input data at at least two resolutions; and inputting the basic image feature into a decoding network to obtain a target image feature for pixel point classification, wherein the decoding network includes at least one cascaded overlapping decoding sub-network to perform decoding and fusion processing on input data at at least two resolutions respectively.

公开(公告)号：US20220392192A1

公开(公告)日：2022-12-08

申请号：US17890020

申请日：2022-08-17

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

Inventor： Zhigang Wang ,  Jian Wang ,  Hao Sun

IPC: G06V10/74 ,  G06V10/98 ,  G06V10/764 ,  G06V40/50 ,  G06V10/77

Abstract: A target re-recognition method, a target re-recognition device and an electronic device are provided, which relate to the field of artificial intelligence, in particularly to the field of computer vision and deep learning. The target re-recognition method includes obtaining a to-be-recognized image, and the to-be-recognized image including image content of a target object; recognizing first appearance presentation information corresponding to the target object, and the first appearance presentation information being configured to represent a presentation form of an appearance of the target object in the to-be-recognized image; obtaining from a data retrieval library a candidate retrieval image matching the first appearance presentation information; and performing target re-recognition on the to-be-recognized image based on the candidate retrieval image.

公开(公告)号：US20230017578A1

公开(公告)日：2023-01-19

申请号：US17935712

申请日：2022-09-27

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

Inventor： Xiangbo Su ,  Jian Wang ,  Hao Sun

IPC: G06T7/70 ,  G06V10/44 ,  G06V10/764 ,  G06V10/771 ,  G06V10/80

Abstract: An image processing and model training methods, an electronic device, and a storage medium are provided, and relate to the technical field of artificial intelligence, and in particular to the technical fields of computer vision and deep learning, which can be specifically applied to smart cities and intelligent cloud scenes. The image processing method includes: obtaining at least one first feature map of an image to be processed, wherein feature data of a target pixel in the first feature map is generated according to the target pixel and another pixel within a set range around the target pixel; determining a classification to which the target pixel belongs according to the feature data of the target pixel; and determining a target object corresponding to the target pixel and association information of the target object according to the classification to which the target pixel belongs.

公开(公告)号：US20230047628A1

公开(公告)日：2023-02-16

申请号：US17976668

申请日：2022-10-28

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

Inventor： Desen ZHOU ,  Jian Wang ,  Hao Sun

IPC: G06V20/52 ,  G06V40/20 ,  G06V20/40

Abstract: A human-object interaction detection method, a neural network and a training method therefor is provided. The human-object interaction detection method includes: performing first target feature extraction on image features of an image to obtain first target features; performing first interaction feature extraction on image features to obtain first interaction features and scores thereof; determining at least some first interaction features in the first interaction features based on the score of each of the first interaction features; determining first motion features based on the at least some first interaction features and the image features; processing the first target features to obtain target information of targets in the image; processing the first motion features to obtain motion information of one or more motions in the image; and matching the targets with the motions to obtain a human-object interaction detection result.