公开(公告)号：US10984246B2

公开(公告)日：2021-04-20

申请号：US16352605

申请日：2019-03-13

Applicant: Google LLC

Inventor： Sharadh Ramaswamy ,  Sourish Chaudhuri ,  Joseph Roth

IPC: G06K9/00 ,  G06F40/169 ,  G06K9/62 ,  G06N3/08

Abstract: Implementations described herein relate to methods, devices, and computer-readable media to perform gating for video analysis. In some implementations, a computer-implemented method includes obtaining a video comprising a plurality of frames and corresponding audio. The method further includes performing sampling to select a subset of the plurality of frames based on a target frame rate and extracting a respective audio spectrogram for each frame in the subset of the plurality of frames. The method further includes reducing resolution of the subset of the plurality of frames. The method further includes applying a machine-learning based gating model to the subset of the plurality of frames and corresponding audio spectrograms and obtaining, as output of the gating model, an indication of whether to analyze the video to add one or more video annotations.

公开(公告)号：US20200293783A1

公开(公告)日：2020-09-17

申请号：US16352605

申请日：2019-03-13

Applicant: Google LLC

Inventor： Sharadh Ramaswamy ,  Sourish Chaudhuri ,  Joseph Roth

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08 ,  G06F17/24

Abstract: Implementations described herein relate to methods, devices, and computer-readable media to perform gating for video analysis. In some implementations, a computer-implemented method includes obtaining a video comprising a plurality of frames and corresponding audio. The method further includes performing sampling to select a subset of the plurality of frames based on a target frame rate and extracting a respective audio spectrogram for each frame in the subset of the plurality of frames. The method further includes reducing resolution of the subset of the plurality of frames. The method further includes applying a machine-learning based gating model to the subset of the plurality of frames and corresponding audio spectrograms and obtaining, as output of the gating model, an indication of whether to analyze the video to add one or more video annotations.

公开(公告)号：US11587319B2

公开(公告)日：2023-02-21

申请号：US17216925

申请日：2021-03-30

Applicant: Google LLC

Inventor： Sharadh Ramaswamy ,  Sourish Chaudhuri ,  Joseph Roth

IPC: G06V20/40 ,  G06F40/169 ,  G06K9/62 ,  G06N3/08

Abstract: Implementations described herein relate to methods, devices, and computer-readable media to perform gating for video analysis. In some implementations, a computer-implemented method includes obtaining a video comprising a plurality of frames and corresponding audio. The method further includes performing sampling to select a subset of the plurality of frames based on a target frame rate and extracting a respective audio spectrogram for each frame in the subset of the plurality of frames. The method further includes reducing resolution of the subset of the plurality of frames. The method further includes applying a machine-learning based gating model to the subset of the plurality of frames and corresponding audio spectrograms and obtaining, as output of the gating model, an indication of whether to analyze the video to add one or more video annotations.

公开(公告)号：US20210216778A1

公开(公告)日：2021-07-15

申请号：US17216925

申请日：2021-03-30

Applicant: Google LLC

Inventor： Sharadh Ramaswamy ,  Sourish Chaudhuri ,  Joseph Roth

IPC: G06K9/00 ,  G06F40/169 ,  G06K9/62 ,  G06N3/08

Abstract: Implementations described herein relate to methods, devices, and computer-readable media to perform gating for video analysis. In some implementations, a computer-implemented method includes obtaining a video comprising a plurality of frames and corresponding audio. The method further includes performing sampling to select a subset of the plurality of frames based on a target frame rate and extracting a respective audio spectrogram for each frame in the subset of the plurality of frames. The method further includes reducing resolution of the subset of the plurality of frames. The method further includes applying a machine-learning based gating model to the subset of the plurality of frames and corresponding audio spectrograms and obtaining, as output of the gating model, an indication of whether to analyze the video to add one or more video annotations.