公开(公告)号：US20210264190A1

公开(公告)日：2021-08-26

申请号：US17206351

申请日：2021-03-19

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

Inventor： Xiameng Qin ,  Yulin Li ,  Ju Huang ,  Qunyi Xie ,  Junyu Han

IPC: G06K9/46 ,  G06K9/62 ,  G06F40/211 ,  G06F16/53

Abstract: The present application discloses an image questioning and answering method, apparatus, device and storage medium, relating to the technical field of image processing, computer vision, deep learning and natural language processing. The specific implementation solution is as follows: constructing a question graph with a topological structure and extracting a question feature of a query sentence, according to the query sentence; constructing a visual graph with a topological structure and a text graph with a topological structure according to a target image corresponding to the query sentence; performing fusion on the visual graph, the text graph and the question graph by using a fusion model, to obtain a final fusion graph; and determining reply information of the query sentence according to a reasoning feature extracted from the final fusion graph and the question feature.

公开(公告)号：US11881044B2

公开(公告)日：2024-01-23

申请号：US17353540

申请日：2021-06-21

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

Inventor： Chengquan Zhang ,  Mengyi En ,  Ju Huang ,  Qunyi Xie ,  Xiameng Qin ,  Kun Yao ,  Junyu Han ,  Jingtuo Liu ,  Errui Ding

IPC: G06V30/414 ,  G06T7/136 ,  G06T7/11 ,  G06F18/213 ,  G06V30/146 ,  G06V30/18 ,  G06V10/764 ,  G06V10/82 ,  G06V30/10

CPC classification number: G06V30/414 ,  G06F18/213 ,  G06T7/11 ,  G06T7/136 ,  G06V10/764 ,  G06V10/82 ,  G06V30/147 ,  G06V30/18057 ,  G06T2207/30176 ,  G06V30/10

Abstract: A method and apparatus for processing an image, a device and a storage medium are provided. An implementation of the method includes: acquiring a template image, the template image including at least one region of interest; determining a first feature map corresponding to each region of interest in the template image; acquiring a target image; determining a second feature map of the target image; and determining at least one region of interest in the target image according to the first feature map and the second feature map.