公开(公告)号：US10991141B2

公开(公告)日：2021-04-27

申请号：US16655991

申请日：2019-10-17

Applicant: Adobe Inc.

Inventor： Abhishek Shah ,  Andaleeb Fatima

IPC: G06T7/73 ,  G06T11/60 ,  G06K9/00

Abstract: Systems and techniques are disclosed for automatically creating a group shot image by intelligently selecting a best frame of a video clip to use as a base frame and then intelligently merging features of other frames into the base frame. In an embodiment, this involves determining emotional alignment scores and eye scores for the individual frames of the video clip. The emotional alignment scores for the frames are determined by assessing the faces in each of the frames with respect to an emotional characteristic (e.g., happy, sad, neutral, etc.). The eye scores for the frames are determined based on assessing the states of the eyes (e.g., fully open, partially open, closed, etc.) of the faces in individual frames. Comprehensive scores for the individual frames are determined based on the emotional alignment scores and the eye scores, and the frame having the best comprehensive score is selected as the base frame.

公开(公告)号：US20200051300A1

公开(公告)日：2020-02-13

申请号：US16655991

申请日：2019-10-17

Applicant: Adobe Inc.

Inventor： Abhishek Shah ,  Andaleeb Fatima

IPC: G06T11/60 ,  G06K9/00 ,  G06T7/73

Abstract: Systems and techniques are disclosed for automatically creating a group shot image by intelligently selecting a best frame of a video clip to use as a base frame and then intelligently merging features of other frames into the base frame. In an embodiment, this involves determining emotional alignment scores and eye scores for the individual frames of the video clip. The emotional alignment scores for the frames are determined by assessing the faces in each of the frames with respect to an emotional characteristic (e.g., happy, sad, neutral, etc.). The eye scores for the frames are determined based on assessing the states of the eyes (e.g., fully open, partially open, closed, etc.) of the faces in individual frames. Comprehensive scores for the individual frames are determined based on the emotional alignment scores and the eye scores, and the frame having the best comprehensive score is selected as the base frame.

公开(公告)号：US10475222B2

公开(公告)日：2019-11-12

申请号：US15695924

申请日：2017-09-05

Applicant: ADOBE INC.

Inventor： Abhishek Shah ,  Andaleeb Fatima

IPC: G06K9/36 ,  G06T11/60 ,  G06K9/00 ,  G06T7/73

Abstract: Systems and techniques are disclosed for automatically creating a group shot image by intelligently selecting a best frame of a video clip to use as a base frame and then intelligently merging features of other frames into the base frame. In an embodiment, this involves determining emotional alignment scores and eye scores for the individual frames of the video clip. The emotional alignment scores for the frames are determined by assessing the faces in each of the frames with respect to an emotional characteristic (e.g., happy, sad, neutral, etc.). The eye scores for the frames are determined based on assessing the states of the eyes (e.g., fully open, partially open, closed, etc.) of the faces in individual frames. Comprehensive scores for the individual frames are determined based on the emotional alignment scores and the eye scores, and the frame having the best comprehensive score is selected as the base frame.

公开(公告)号：US10276213B2

公开(公告)日：2019-04-30

申请号：US15602006

申请日：2017-05-22

Applicant: ADOBE INC.

Inventor： Sagar Tandon ,  Andaleeb Fatima ,  Abhishek Shah

IPC: H04N9/80 ,  G11B27/34 ,  G06K9/00 ,  G11B27/031 ,  G11B27/22 ,  G06F16/78 ,  G06F16/783

Abstract: Systems and methods disclosed herein provide automatic and intelligent video sorting in the context of creating video compositions. A computing device sorts a media bin of videos in the user's work area based on similarity to the videos included in the video composition being created. When a user selects or includes a particular video on the composition's timeline, the video is compared against the entire video collection to change the display of videos in the media bin. In one example, videos that have similar tags to a selected video are prioritized at the top. Only a subset of frames of each of the videos are used to use to identify video tags. Intelligently selecting tags using a subset of frames from each video rather than using all frames enables more efficient and accurate tagging of videos, which facilitates quicker and more accurate comparison of video similarities.