公开(公告)号：US11430219B2

公开(公告)日：2022-08-30

申请号：US16952675

申请日：2020-11-19

Applicant: Adobe Inc.

Inventor： Somdeb Sarkhel ,  Viswanathan Swaminathan ,  Stefano Petrangeli ,  Md Maminur Islam

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

Abstract: Systems and methods predict a performance metric for a video and identify key portions of the video that contribute to the performance metric, which can be used to edit the video to improve the ultimate viewer response to the video. An initial performance metric is computed for an initial video (e.g., using a neural network). A perturbed video is generated by perturbing a video portion of the initial video. A modified performance metric is computed for the perturbed video. Based on a difference between the initial and modified performance metrics, the system determines that the video portion contributed to a predicted user viewer response to the initial video. An indication of the video portion that contributed to the predicted user viewer response is provided as output, which can be used to edit the video to improve the predicted viewer response.

公开(公告)号：US20220156499A1

公开(公告)日：2022-05-19

申请号：US16952675

申请日：2020-11-19

Applicant: Adobe Inc.

Inventor： Somdeb Sarkhel ,  Viswanathan Swaminathan ,  Stefano Petrangeli ,  Md Maminur Islam

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62

Abstract: Systems and methods predict a performance metric for a video and identify key portions of the video that contribute to the performance metric, which can be used to edit the video to improve the ultimate viewer response to the video. An initial performance metric is computed for an initial video (e.g., using a neural network). A perturbed video is generated by perturbing a video portion of the initial video. A modified performance metric is computed for the perturbed video. Based on a difference between the initial and modified performance metrics, the system determines that the video portion contributed to a predicted user viewer response to the initial video. An indication of the video portion that contributed to the predicted user viewer response is provided as output, which can be used to edit the video to improve the predicted viewer response.