IP Library Granted Patent US 10,945,042
Granted Patent B2
US 10,945,042 · App. 16/195,458 · Granted Mar 9, 2021

Generating an interactive digital video content item

Inventors: Richard Rabbat (Palo Alto, CA); Ernestine Fu (Northridge, CA)
Assignee: Gfycat, Inc.
H04N21/4725G06K9/00228G06K9/00744G11B27/036H04N21/44008H04N21/8545H04N21/8586
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 10,945,042
App. No.
16/195,458
Granted
Mar 9, 2021
Kind
B2
Abstract

In a computer-implemented method for generating an interactive digital video content item, a digital video content item is accessed. Subject recognition is performed on the digital video content item, wherein the subject recognition automatically identifies a visual subject within the digital video content item. Responsive to identifying the visual subject, an interactive region is applied to visual subject within the digital video content item, wherein the interactive region enables presentation of content related to the visual subject in response to a user interaction with the interactive region during presentation of the digital video content item.

Claims (47)

1. A method for generating an interactive digital video content item, the method comprising:

accessing a digital video content item;

performing facial recognition on a face of a human visual subject in the digital video content item to identify a person corresponding to the visual subject;

in response to the facial recognition being unable to identify the person, performing subject recognition on the digital video content item, wherein the subject recognition automatically identifies the visual subject within the digital video content item as a category of human; and

responsive to identifying the visual subject as a particular person or as a category of human, applying an interactive region to the visual subject within the digital video content item such that the interactive region overlays at least a portion of the visual subject and defines an area of the digital video content item for receiving a user interaction during presentation of the digital video content item, wherein the interactive region enables presentation of content related to the visual subject in response to a user interaction with the interactive region during presentation of the digital video content item, wherein the digital video content item is a short form looping prerecorded video file.

2. The method of claim 1 , wherein the category of human comprises a teenager.

3. The method of claim 1 , further comprising performing object recognition on a visual object in the digital video content item, wherein the object recognition automatically identifies the visual object within the digital video content item.

4. The method of claim 3 further comprising, responsive to identifying the visual object, applying an interactive region to the visual object within the digital video content item such that the interactive region overlays at least a portion of the visual object and defines an area of the digital video content item for receiving a user interaction during presentation of the digital video content item, wherein the interactive region enables presentation of content related to the visual object in response to a user interaction with the interactive region during presentation of the digital video content item.

5. The method of claim 1 , wherein the performing subject recognition on the digital video content item comprises:

accessing a library of recognizable visual subjects;

comparing the visual subject to the library of recognizable visual subjects; and

identifying the visual subject as a recognizable visual subject of the library of recognizable visual subjects.

6. The method of claim 1 , further comprising:

displaying the digital video content item comprising the interactive region on a display device of an electronic device; and

responsive to detecting an interaction with the interactive region, presenting the content related to the visual subject.

7. A non-transitory computer readable storage medium having computer readable program code stored thereon for causing a computer system to perform a method for generating an interactive digital video content item, the method comprising:

accessing a digital video content item;

performing facial recognition on a face of a human visual subject in the digital video content item to identify a person corresponding to the visual subject;

in response to the facial recognition being unable to identify the person, performing subject recognition on the digital video content item, wherein the subject recognition automatically identifies the visual subject within the digital video content item as a category of human; and

responsive to identifying the visual subject as a particular person or as a category of human, applying an interactive region to the visual subject within the digital video content item such that the interactive region overlays at least a portion of the visual subject and defines an area of the digital video content item for receiving a user interaction during presentation of the digital video content item, wherein the interactive region enables presentation of content related to the visual subject in response to a user interaction with the interactive region during presentation of the digital video content item.

8. The non-transitory computer readable storage medium of claim 7 , wherein the category of human comprises a teenager.

9. The non-transitory computer readable storage medium of claim 7 , the method further comprising performing object recognition on a visual object in the digital video content item, wherein the object recognition automatically identifies the visual object within the digital video content item.

10. The non-transitory computer readable storage medium of claim 9 , the method further comprising, responsive to identifying the visual object, applying an interactive region to the visual object within the digital video content item such that the interactive region overlays at least a portion of the visual object and defines an area of the digital video content item for receiving a user interaction during presentation of the digital video content item, wherein the interactive region enables presentation of content related to the visual object in response to a user interaction with the interactive region during presentation of the digital video content item.

11. The non-transitory computer readable storage medium of claim 7 , wherein the performing subject recognition on the digital video content item comprises:

accessing a library of recognizable visual subjects;

comparing the visual subject to the library of recognizable visual subjects; and

identifying the visual subject as a recognizable visual subject of the library of recognizable visual subjects.

12. The non-transitory computer readable storage medium of claim 7 , the method further comprising:

displaying the digital video content item comprising the interactive region on a display device of an electronic device; and

responsive to detecting an interaction with the interactive region, presenting the content related to the visual subject.

13. The non-transitory computer readable storage medium of claim 7 , wherein the content comprises a uniform resource locator.

14. The non-transitory computer readable storage medium of claim 7 , wherein the digital video content item is a short form looping prerecorded video file.

15. A computer system comprising:

a data storage unit; and

a processor coupled with the data storage unit, the processor configured to:

access a digital video content item;

perform facial recognition on a face of a human visual subject in a digital video content item to identify a person corresponding to the visual subject;

in response to the facial recognition being unable to identify the person, perform subject recognition on the digital video content item, wherein the subject recognition automatically identifies the visual subject within the digital video content item as a category of human; and

responsive to identifying the visual subject as a particular person or as a category of human, apply an interactive region to the visual subject within the digital video content item such that the interactive region overlays at least a portion of the visual subject and defines an area of the digital video content item for receiving a user interaction during presentation of the digital video content item, wherein the interactive region enables presentation of content related to the visual subject in response to a user interaction with the interactive region during presentation of the digital video content item.

16. The computer system of claim 15 , wherein the category of human comprises a teenager.

17. The computer system of claim 15 , wherein the processor is further configured to perform object recognition on a visual object in the digital video content item, wherein the object recognition automatically identifies the visual object within the digital video content item.

18. The computer system of claim 15 , wherein the processor is further configured to

access a library of recognizable visual subjects;

compare the visual subject to the library of recognizable visual subjects; and

identify the visual subject as a recognizable visual subject of the library of recognizable visual subjects.

19. The computer system of claim 15 , wherein the content comprises a uniform resource locator.

20. The computer system of claim 15 , wherein the digital video content item is a short form looping prerecorded video file.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 3, 2022
From: GFYCAT, INC.
To: SNAP INC.
Reel/Frame 061963/0865 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 19, 2018
From: RABBAT, RICHARD; FU, ERNESTINE
To: GFYCAT, INC.
Reel/Frame 047547/0550 →
Continuity (1)
Related Publication 20200162792A1 · May 21, 2020