公开(公告)号：US12283291B1

公开(公告)日：2025-04-22

申请号：US18450695

申请日：2023-08-16

Applicant: Amazon Technologies, Inc.

Inventor： Noah Lirone Sarfati ,  Ido Yerushalmy ,  Michael Chertok ,  Ianir Ideses

IPC: G11B27/036 ,  G10L15/26 ,  H04N21/81 ,  H04N21/8549

Abstract: Systems, devices, and methods are provided for determining factually consistent generative narrations. A narrative may be generated by performing steps to determine one or more metadata messages for a first portion of a video stream, determine transcribed commentary for a second portion of the video stream, wherein the second portion includes the first portion, and determine a prompt based at least in part on the one or more metadata messages and the transcribed commentary. The prompt may be provided to a generative model that produces an output text. Techniques for performing a factual consistency evaluation may be used to determine a consistency score for the output text that indicates whether the output text is factually consistent with the one or more metadata messages and the transcribed commentary. A narrated highlight video may be generated using the consistent narrative.

公开(公告)号：US11961331B1

公开(公告)日：2024-04-16

申请号：US17446390

申请日：2021-08-30

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Ido Yerushalmy ,  Michael Chertok ,  Sharon Alpert

IPC: G06V40/20 ,  G06N20/00 ,  G06T7/73 ,  G06V10/98 ,  G06V20/40

CPC classification number: G06V40/23 ,  G06N20/00 ,  G06T7/73 ,  G06V10/993 ,  G06V20/46 ,  G06T2207/10016 ,  G06T2207/20081

Abstract: A first computing device acquires video data representing a user performing an activity. The first device uses a first pose extraction algorithm to determine a pose of the user within a frame of video data. If the pose is determined to be potentially inaccurate, the user is prompted for authorization to send the frame of video data to a second computing device. If authorization is granted, the second computing device may use a different algorithm to determine a pose of the user and send data indicative of this pose to the first computing device to enable the first computing device to update a score or other output. The second computing device may also use the frame of video data as training data to retrain or modify the first pose extraction algorithm, and may send the modified algorithm to the first computing device for future use.