公开(公告)号：US12198397B2

公开(公告)日：2025-01-14

申请号：US17586284

申请日：2022-01-27

Applicant: NEC Laboratories America, Inc.

Inventor： Asim Kadav ,  Farley Lai ,  Hans Peter Graf ,  Yi Huang

IPC: G06V10/26 ,  G06T7/246 ,  G06V10/44 ,  G06V10/82 ,  G06V20/58 ,  G06V40/10 ,  G08G1/16

Abstract: A computer-implemented method is provided for action localization. The method includes converting one or more video frames into person keypoints and object keypoints. The method further includes embedding position, timestamp, instance, and type information with the person keypoints and object keypoints to obtain keypoint embeddings. The method also includes predicting, by a hierarchical transformer encoder using the keypoint embeddings, human actions and bounding box information of when and where the human actions occur in the one or more video frames.

公开(公告)号：US20220237884A1

公开(公告)日：2022-07-28

申请号：US17586284

申请日：2022-01-27

Applicant: NEC Laboratories America, Inc.

Inventor： Asim Kadav ,  Farley Lai ,  Hans Peter Graf ,  Yi Huang

IPC: G06V10/26 ,  G06T7/246 ,  G06V40/10 ,  G06V10/44 ,  G06V10/82 ,  G06V20/58 ,  G08G1/16

Abstract: A computer-implemented method is provided for action localization. The method includes converting one or more video frames into person keypoints and object keypoints. The method further includes embedding position, timestamp, instance, and type information with the person keypoints and object keypoints to obtain keypoint embeddings. The method also includes predicting, by a hierarchical transformer encoder using the keypoint embeddings, human actions and bounding box information of when and where the human actions occur in the one or more video frames.