公开(公告)号：US20240221356A1

公开(公告)日：2024-07-04

申请号：US18397203

申请日：2023-12-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ping WEI ,  Changkai LI ,  Ruijie ZHANG ,  Yuxin WANG ,  Huan LI ,  Han XU ,  Ran YANG ,  Yuanyuan ZHANG

IPC: G06V10/764

CPC classification number: G06V10/764

Abstract: A processor-implemented method including extracting initial feature maps from respective images extracted from a video, wherein the extracting of the initial features maps is performed using a transformer, generating a target feature map by fusing the initial feature maps using a feature fusion network including one or more layers, and identifying an object in the video based on the target feature map.