公开(公告)号：US20190114487A1

公开(公告)日：2019-04-18

申请号：US15782789

申请日：2017-10-12

Applicant: Google LLC

Inventor： Sudheendra Vijayanarasimhan ,  Alexis Bienvenu ,  David Ross ,  Timothy Novikoff ,  Arvind Balasubramanian

IPC: G06K9/00 ,  G06N3/04 ,  G06F3/0484

Abstract: A computer-implemented method includes receiving a video that includes multiple frames. The method further includes identifying a start time and an end time of each action in the video based on application of one or more of an audio classifier, an RGB classifier, and a motion classifier. The method further includes identifying video segments from the video that include frames between the start time and the end time for each action in the video. The method further includes generating a confidence score for each of the video segments based on a probability that a corresponding action corresponds to one or more of a set of predetermined actions. The method further includes selecting a subset of the video segments based on the confidence score for each of the video segments.

公开(公告)号：US10740620B2

公开(公告)日：2020-08-11

申请号：US15782789

申请日：2017-10-12

Applicant: Google LLC

Inventor： Sudheendra Vijayanarasimhan ,  Alexis Bienvenu ,  David Ross ,  Timothy Novikoff ,  Arvind Balasubramanian

IPC: G06K9/00 ,  G06F3/0484 ,  G06N3/04

Abstract: A computer-implemented method includes receiving a video that includes multiple frames. The method further includes identifying a start time and an end time of each action in the video based on application of one or more of an audio classifier, an RGB classifier, and a motion classifier. The method further includes identifying video segments from the video that include frames between the start time and the end time for each action in the video. The method further includes generating a confidence score for each of the video segments based on a probability that a corresponding action corresponds to one or more of a set of predetermined actions. The method further includes selecting a subset of the video segments based on the confidence score for each of the video segments.

公开(公告)号：US11663827B2

公开(公告)日：2023-05-30

申请号：US17863445

申请日：2022-07-13

Applicant: Google LLC

Inventor： Sudheendra Vijayanarasimhan ,  Alexis Bienvenu ,  David Ross ,  Timothy Novikoff ,  Arvind Balasubramanian

IPC: G06V20/40 ,  G06F3/0484 ,  G06N3/04 ,  G06V20/30

CPC classification number: G06V20/47 ,  G06F3/0484 ,  G06N3/04 ,  G06V20/30 ,  G06V20/41 ,  G06V20/44

Abstract: A computer-implemented method includes receiving a video that includes multiple frames. The method further includes identifying a start time and an end time of each action in the video based on application of one or more of an audio classifier, an RGB classifier, and a motion classifier. The method further includes identifying video segments from the video that include frames between the start time and the end time for each action in the video. The method further includes generating a confidence score for each of the video segments based on a probability that a corresponding action corresponds to one or more of a set of predetermined actions. The method further includes selecting a subset of the video segments based on the confidence score for each of the video segments.

公开(公告)号：US20220351516A1

公开(公告)日：2022-11-03

申请号：US17863445

申请日：2022-07-13

Applicant: Google LLC

Inventor： Sudheendra Vijayanarasimhan ,  Alexis Bienvenu ,  David Ross ,  Timothy Novikoff ,  Arvind Balasubramanian

IPC: G06V20/40 ,  G06F3/0484 ,  G06N3/04 ,  G06V20/30

Abstract: A computer-implemented method includes receiving a video that includes multiple frames. The method further includes identifying a start time and an end time of each action in the video based on application of one or more of an audio classifier, an RGB classifier, and a motion classifier. The method further includes identifying video segments from the video that include frames between the start time and the end time for each action in the video. The method further includes generating a confidence score for each of the video segments based on a probability that a corresponding action corresponds to one or more of a set of predetermined actions. The method further includes selecting a subset of the video segments based on the confidence score for each of the video segments.