公开(公告)号：US20210081695A1

公开(公告)日：2021-03-18

申请号：US16967220

申请日：2019-12-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Xiaobing WANG ,  Yingying JIANG ,  Xiangyu ZHU ,  Hao GUO ,  Yi YU ,  Pingjun LI ,  Zhenbo LUO

IPC: G06K9/32 ,  G06K9/46 ,  G06N3/04 ,  G06T7/13

Abstract: The present application discloses an image processing method, apparatus, electronic device and computer readable storage medium. The image processing method comprises detecting a text region in an image to be processed, recognizing the text region to obtain a text recognition result. In this application, the text recognition in the image to be processed is realized, the recognition manner for the text in the image is simplified, and the recognition effect for the text is improved.

公开(公告)号：US20220327834A1

公开(公告)日：2022-10-13

申请号：US17843603

申请日：2022-06-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Shizhuo LIU ,  Jingjun JIAO ,  Xiaobing WANG ,  Lanlan ZHANG ,  Wei LI ,  Haifeng ZHANG ,  Zhezhu JIN ,  Wei WEN

IPC: G06V20/40 ,  G06V40/20 ,  G06T7/246

Abstract: An action localization method, device, electronic equipment, and computer-readable storage medium are provided. The action localization method includes: identifying at least one target video segment containing a target object in a video; acquiring a first action recognition result of at least one image frame in the at least one target video segment and a second action recognition result of the target video segment; and acquiring an action localization result of the video based on the first action recognition result and the second action recognition result.

公开(公告)号：US20210210119A1

公开(公告)日：2021-07-08

申请号：US17140732

申请日：2021-01-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hanchao JIA ,  Luman MA ,  Xiaobing WANG ,  Yingying JIANG ,  Bo ZHU

IPC: G11B27/06 ,  G06K9/00 ,  G11B27/10 ,  G11B27/031 ,  G11B27/34

Abstract: A video generation method includes obtaining action clips into which source videos are split, through action recognition with respect to the source videos, selecting target clips from among the action clips, based on correlation between clip features of at least some of the action clips and an intention feature extracted from a video generation request, and generating a target video by combining at least some of the target clips.