IP Library › Granted Patent US 12,277,955
Granted Patent B2
US 12,277,955 · App. 18/208,680 · Granted Apr 15, 2025

Generation of a collection of video clips

Inventors: Alexander Collins (Santa Monica, CA); Alexander Vodovoz (Inglewood, CA)
Assignee: Snap Inc.
G11B27/036G11B27/034G11B27/34H04N5/783H04N21/8455H04N21/8547H04N21/8549
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,277,955
App. No.
18/208,680
Granted
Apr 15, 2025
Kind
B2
Abstract

A method for generation of a collection of video clips from a plurality of video files includes performing facial recognition on a video file of the plurality of video files to identify a portion of the video file including a face, generating a video clip by trimming the portion of the video file including the face, from the video file, and adding the video clip to the collection of video clips. A video montage may be created by adding a plurality of video clips from the collection of video clips together and adding an audio track to the video montage file.

Claims (74)

1. A method, executed by one or more processors, for generation of a video montage from a collection of video clips taken from a plurality of video files, comprising:

performing facial recognition on a video file of the plurality of video files to identify a portion of the video file including a face;

determining a relevance of the face in the portion of the video file;

generating a video clip by trimming the portion of the video file including the face, from the video file, a length of the video clip being based on the relevance of the face in the video file; and

adding the video clip to the video montage, wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to a first length based on the face being less relevant; and

trimming the portion of the video file to a second length that is greater than the first length based on the face being more relevant.

2. The method of claim 1 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the face not being a close up of the face; and

trimming the portion of the video file to the second length that is greater than the first length based on the face being a close up of the face.

3. The method of claim 1 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion of the video file not including speech; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion including the face as well as speech.

4. The method of claim 1 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion not including a face of a user of a device including at least one of the one or more processors; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion of the video file including a face of the user of the device.

5. The method of claim 1 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion not including a face of a person having a relationship with a user of a device including at least one of the one or more processors; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion including a face of a person having a relationship with the user of a device.

6. The method of claim 1 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file that includes the face but not a caption to the first length; and

trimming the portion of the video file that includes the face, as well as a caption to the second length that is greater than the first length.

7. The method of claim 1 , further comprising:

creating a video montage file by adding a plurality of video clips from the collection of video clips together; and

adding an audio track to the video montage file.

8. A computing apparatus comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, configure the computing apparatus to perform operations to generate a video montage from a collection of video clips taken from a plurality of video files, the operations comprising:

performing facial recognition on a video file of the plurality of video files to identify a portion of the video file including a face;

determining a relevance of the face in the portion of the video file;

generating a video clip by trimming the portion of the video file including the face, from the video file, a length of the video clip being based on the relevance of the face in the video file; and

adding the video clip to the video montage, wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to a first length based on the face being less relevant; and

trimming the portion of the video file to a second length that is greater than the first length based on the face being more relevant.

9. The computing apparatus of claim 8 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the face not being a close up of the face; and

trimming the portion of the video file to a second length that is greater than the first length based on the face being a close up of the face.

10. The computing apparatus of claim 8 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion of the video file not including speech; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion including the face as well as speech.

11. The computing apparatus of claim 8 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion not including a face of a user of the computing apparatus; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion of the video file including a face of the user of the computing apparatus.

12. The computing apparatus of claim 8 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion not including a face of a person having a relationship with a user of the computing apparatus; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion including a face of a person having a relationship with the user of a device.

13. The computing apparatus of claim 8 , wherein the operations further comprise:

creating a video montage file by adding a plurality of video clips from the collection of video clips together; and

adding an audio track to the video montage file.

14. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform operations to generate a video montage from a collection of video clips taken from a plurality of video files, the operations comprising:

performing facial recognition on a video file of the plurality of video files to identify a portion of the video file including a face;

determining a relevance of the face in the portion of the video file;

generating a video clip by trimming the portion of the video file including the face, from the video file, a length of the video clip being based on the relevance of the face in the video file; and

adding the video clip to the video montage, wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to a first length based on the face being less relevant; and

trimming the portion of the video file to a second length that is greater than the first length based on the face being more relevant.

15. The computer-readable storage medium of claim 14 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the face not being a close up of the face; and

trimming the portion of the video file to the second length that is greater than the first length based on the face being a close up of the face.

16. The computer-readable storage medium of claim 14 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion of the video file not including speech; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion including the face as well as speech.

17. The computer-readable storage medium of claim 14 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion not including a face of a user of the computer; and

trimming the portion of the video file to the second length that is greater than the first length based on the portion of the video file including a face of the user the computer.

18. The computer-readable storage medium of claim 14 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file to the first length based on the portion not including a face of a person having a relationship with a user of the computer; and

trimming the portion of the video file to a second length that is greater than the first length based on the portion including a face of a person having a relationship with the user of a device.

19. The computer-readable storage medium of claim 14 , wherein trimming the portion of the video file including a face comprises:

trimming the portion of the video file that includes the face but not a caption to the first length; and

trimming the portion of the video file that includes the face, as well as a caption to the second length that is greater than the first length.

20. The computer-readable storage medium of claim 14 , wherein the operations further comprise:

creating a video montage file by adding a plurality of video clips from the collection of video clips together; and

adding an audio track to the video montage file.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 28, 2025
From: COLLINS, ALEXANDER; VODOVOZ, ALEXANDER
To: SNAP INC.
Reel/Frame 070034/0531 →
Continuity (4)
Continuation 17546726 · Dec 9, 2021
Continuation 17307458 · May 4, 2021
Provisional Application 63168500 · Mar 31, 2021
Related Publication 20230326490A1 · Oct 12, 2023
References Cited (50)
US 6871006B1 · Oguz et al. · 2005 [cited by applicant]
US 7362946B1 · Kowald · 2008 [cited by applicant]
US 7512886B1 · Herberger et al. · 2009 [cited by applicant]
US 9838730B1 · Matias · 2017 [cited by applicant]
US 10178365B1 · Singh et al. · 2019 [cited by applicant]
US 11163941B1 · Al Majid et al. · 2021 [cited by applicant]
US 11227637B1 · Collins et al. · 2022 [cited by applicant]
US 11721367B2 · Collins et al. · 2023 [cited by applicant]
US 20030160944A1 · Foote et al. · 2003 [cited by applicant]
US 20080016114A1 · Beauregard et al. · 2008 [cited by applicant]
US 20080092168A1 · Logan et al. · 2008 [cited by applicant]
US 20100183280A1 · Beauregard et al. · 2010 [cited by applicant]
US 20130077937A1 · Kennedy et al. · 2013 [cited by applicant]
US 20150160916A1 · Lothian · 2015 [cited by applicant]
US 20150279427A1 · Godfrey et al. · 2015 [cited by applicant]
US 20160071549A1 · Von Sneidern et al. · 2016 [cited by applicant]
US 20160155475A1 · Hamer · 2016 [cited by examiner]
US 20170017658A1 · Blong · 2017 [cited by examiner]
US 20180068019A1 · Novikoff et al. · 2018 [cited by applicant]
US 20180295396A1 · Ramadorai · 2018 [cited by examiner]
US 20190392866A1 · Yoon et al. · 2019 [cited by applicant]
US 20200358731A1 · Boyd et al. · 2020 [cited by applicant]
US 20200366395A1 · Brenner et al. · 2020 [cited by applicant]
US 20210144422A1 · Wagner et al. · 2021 [cited by applicant]
US 20210350131A1 · Ouimet et al. · 2021 [cited by applicant]
US 20220131948A1 · Al Majid et al. · 2022 [cited by applicant]
US 20220293133A1 · Spreitzer et al. · 2022 [cited by applicant]
US 20220318566A1 · Krishnan Gorumkonda · 2022 [cited by applicant]
US 20220319552A1 · Collins et al. · 2022 [cited by applicant]
CN 105814634A · 2016 [cited by applicant]
CN 110572722A · 2019 [cited by applicant]
CN 111669625A · 2020 [cited by applicant]
CN 117157710 · 2023 [cited by applicant]
EP 1587111A1 · 2005 [cited by applicant]
WO 2022212127 · 2022 [cited by applicant]
WO WO2022212127A1 · 2022 [cited by applicant]
“U.S. Appl. No. 17/307,458, Notice of Allowance mailed Sep. 14, 2021”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 17/546,726, Notice of Allowance mailed Mar. 13, 2023”, 12 pgs. [cited by applicant]
“International Application Serial No. PCT/US2022/021345, International Search Report mailed Jul. 21, 2022”, 4 pgs. [cited by applicant]
“International Application Serial No. PCT/US2022/021345, Written Opinion mailed Jul. 21, 2022”, 6 pgs. [cited by applicant]
“International Application Serial No. PCT/US2022/021345, International Preliminary Report on Patentability mailed Oct. 12, 2023”, 9 pgs. [cited by applicant]
“Chinese Application Serial No. 202280026550.3, Voluntary Amendment filed Mar. 5, 2024”, w/ English Translation of Claims, 17 pgs. [cited by applicant]
“Chinese Application Serial No. 202280026550.3, Office Action mailed Mar. 28, 2024”, w/ English translation, 13 pgs. [cited by applicant]
U.S. Appl. No. 17/307,458, U.S. Pat. No. 11,227,637, filed May 4, 2021, Synchronizing Multiple Images Or Videos To An Audio Track. [cited by applicant]
U.S. Appl. No. 17/546,726, U.S. Pat. No. 11,721,367, filed Dec. 9, 2021, Synchronizing Multiple Images Or Videos To An Audio Track. [cited by applicant]
U.S. Appl. No. 18/484,326, filed Oct. 10, 2023, Sound Sync On Video Montages. [cited by applicant]
“International Application Serial No. PCT/US2024/030873, International Search Report mailed Aug. 29, 2024”, 4 pgs. [cited by applicant]
“International Application Serial No. PCT/US2024/030873, Written Opinion mailed Aug. 29, 2024”, 4 pgs. [cited by applicant]
“Korean Application Serial No. 10-2023-7036252, Notice of Preliminary Rejection mailed Jul. 26, 2024”, w/ English translation, 9 pgs. [cited by applicant]
“U.S. Appl. No. 18/484,326, Non Final Office Action mailed Jan. 30, 2025”, 8 pgs. [cited by applicant]