公开(公告)号：US11151386B1

公开(公告)日：2021-10-19

申请号：US16809421

申请日：2020-03-04

Applicant: Amazon Technologies, Inc.

Inventor： Abhinav Aggarwal ,  Heena Bansal ,  Lokesh Amarnath Ravindranathan ,  Yash Pandya ,  Muhammad Raffay Hamid ,  Manivel Sethu

IPC: G06K9/00 ,  H04N21/44 ,  G06F16/78 ,  G06F16/75 ,  G06F16/783

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for automated identification and tagging of video content. Example methods may include determining a first set of frames in video content, determining a first set of faces that appear in the first set of frames, and extracting first image content corresponding to respective faces of the first set of faces. Methods may include classifying the first image content into a first set of clusters, generating a second set of clusters comprising a second set of faces, wherein the second set of faces has less faces than the first set of faces, and determining a first actor identifier associated with a first face in the second set of clusters. Some methods may include determining second image content in the second set of clusters comprising the first face, and automatically associating the first actor identifier with the second image content.