公开(公告)号：US20250118046A1

公开(公告)日：2025-04-10

申请号：US18985445

申请日：2024-12-18

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

Inventor： Xiaoyun Han ,  Jingming Wang ,  Qiang Xie ,  Tao Li

IPC: G06V10/32 ,  G06V10/42 ,  G06V10/74 ,  G06V10/766 ,  G06V10/77 ,  G06V10/774 ,  G06V40/10

Abstract: Provided is a method for training an image cropping model, a method for processing an image, an electronic device and a storage medium, relating to the field of deep learning and image processing technology. The training method includes: obtaining sample data, wherein the sample data at least includes: a sample image, a first cropped image obtained by cropping the sample image in a first manner, and a second cropped image obtained by cropping the sample image in a second manner; determining a target loss function; and using at least the sample data and the target loss function to perform model training on a preset image cropping model to obtain a target image cropping model.

公开(公告)号：US20250118001A1

公开(公告)日：2025-04-10

申请号：US18988095

申请日：2024-12-19

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

Inventor： Zhaoxu Wang ,  Qiang Xie ,  Yuhang Zheng ,  Tao Li ,  Shouke Qin ,  Zonggang Wu ,  Qian Wu ,  Weijian Jian ,  Ruohan Chang ,  Di Meng ,  Yuanhua Shao ,  Xiaoyun Han ,  Yang Yang

IPC: G06T11/60 ,  G06T7/00 ,  G06T7/11 ,  G06V10/764 ,  G06V10/77 ,  G06V10/776 ,  G06V10/82 ,  G06V30/18 ,  G06V30/262

Abstract: A method for obtaining a cover image includes: obtaining a plurality of first cropped images of an original image corresponding to a candidate resource; obtaining an aesthetic score of each of the plurality of first cropped images; and determining a target cover image of the candidate resource from the plurality of first cropped images based on the aesthetic score of each first cropped image.

公开(公告)号：US20250117602A1

公开(公告)日：2025-04-10

申请号：US18988044

申请日：2024-12-19

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

Inventor： Zhaoxu Wang ,  Qiang Xie ,  Yuhang Zheng ,  Shouke Qin ,  Zonggang Wu ,  Yuanhua Shao ,  Yan Wang ,  Ruohan Chang ,  Qingqing Wu ,  Lu Wang ,  Songge Guo ,  Chang Li ,  Xi Cao ,  Qian Wu ,  Xiaoyu Hu ,  Huijie Liu ,  Yu Guo ,  Hui Xue ,  Rufeng Cheng

IPC: G06F40/40

Abstract: A large model-based recommendation method includes: determining description information of interested content corresponding to a target user; inputting a content to be recommended, the description information of interested content and current popular search sentences into a large model to generate at least one recommendation card corresponding to the content to be recommended, in which the recommendation card contains a recommendation word associated with the content to be recommended; obtaining a current behavior characteristic of the target user; and in response to the current behavior characteristic satisfying a display condition of the recommendation card, displaying the recommendation card corresponding to at least one content to be recommended.