公开(公告)号：US20230196716A1

公开(公告)日：2023-06-22

申请号：US18173689

申请日：2023-02-23

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

Inventor： Yuan FENG ,  Zhun SUN ,  Honghui ZHENG ,  Ying XIN ,  Bin ZHANG ,  Chao LI ,  Yunhao WANG ,  Shumin HAN

IPC: G06V10/44 ,  G06V10/774 ,  G06V10/764

CPC classification number: G06V10/443 ,  G06V10/774 ,  G06V10/764

Abstract: A method for training a multi-target image-text matching model and an image-text retrieval method are provided. The method for training the multi-target image-text matching model includes: obtaining a plurality of training samples that include sample pairs each including a sample image and a sample text, the sample image including a plurality of targets; obtaining, for each of the plurality of training samples, a heat map corresponding to the sample text in the training sample, the heat map representing a region of the target in the sample image that corresponds to the sample text; and training an image-text matching model based on a plurality of the sample texts and corresponding heat maps to obtain the multi-target image-text matching model.