Computerized system and method for automatically extracting GIFs from videos

Patent metadata

Field	Value
Publication number	US-9799373-B2
Application number	US-201514933397-A
Country	US
Kind code	B2
Filing date	Nov 5, 2015
Priority date	Nov 5, 2015
Publication date	Oct 24, 2017
Grant date	Oct 24, 2017

Abstract

Disclosed are systems and methods for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods provide systems and methods for automatically extracting and creating an animated Graphics Interchange Format (GIF) file from a media file. The disclosed systems and methods identify a number of GIF candidates from a video file, and based on analysis of each candidate's attributes, features and/or qualities, as well as determinations related to an optimal playback setting for the content of each GIF candidate, at least one GIF candidate is automatically provided to a user for rendering.

First claim

What is claimed is:

1. A method comprising steps of:
receiving, at a computing device, a request from a user for creation of an animated Graphics Interchange Format (GIF) file from a video file;
determining, via the computing device, a segment within the video file, said segment determination comprising parsing the video file to identify transition frames within the video file, said segment comprising video frames of the video file existing between a pair of identified transition frames;
determining, via the computing device, playback settings for the segment, each playback setting comprising a different frame sampling rate and time interval between each frame of the segment;
determining, via the computing device, an n-dimensional feature vector for the segment, said feature vector determination comprising parsing the segment to identify information associated with motion, emotion and interestingness features of the segment, said feature vector based on the motion, emotion and interestingness information;
determining, via the computing device, a popularity score for each playback setting based on the feature vector, said popularity score determination comprising determining an optimal playback setting for the segment from the playback settings; and
automatically creating, via the computing device, the animated GIF file, said animated GIF file comprising said segment renderable at said optimal playback setting.

2. The method of claim 1 , further comprising:
communicating, via the computing device, said animated GIF file to said user for display on a device of the user.

3. The method of claim 1 , wherein said segment determination further comprising:
determining that said segment comprises a time length at or above a time threshold; and
re-parsing said segment via a multiple change point detection (MCPD) algorithm to identify additional transitional frames within the segment, wherein said segment is in accordance with said additional transitional frames.

4. The method of claim 1 , wherein said parsing of the segment to identify said transition frames comprises applying a frame differencing algorithm.

5. The method of claim 1 , wherein said transition frames comprise a visual effect selected from a group consisting of: a cut between video frames, fade in/out between frames, dissolve and wipe.

6. The method of claim 1 , wherein said playback settings determination further comprising:
determining a frame per second (FPS) value for the segment; and
determining a time interval between frames of the segment for each playback setting by multiplying a positive real number factor to the FPS value.

7. The method of claim 1 , further comprising:
determining said motion information by analyzing attributes of the segment, said attributes comprising shape and appearance changes over time, total aggregate motion energy, and loop likelihood;
determining said emotion information by analyzing intensities of recognized emotions within said segments, said recognized emotions are determined by detecting facial action units within frames of the segment; and
determining said interestingness information by detecting the presence or absence of a set of predefined objects and actions in the frames of the segment.

8. The method of claim 7 , wherein said feature vector determination further comprising:
combining the motion, emotion and interestingness information into said n-dimensional feature vector, said n-dimensional value being a consistent value across each playback setting.

9. The method of claim 1 , wherein said popularity score determination further comprising:
applying a regression function to the feature vector in order to determine the optimal playback setting of the segment, said application of the regression function is based on a trained dataset of known GIFs, wherein said known GIFs have associated therewith popularity scores based on interactions by users over a network, wherein said popularity scores of the known GIFs are further based on motion, emotion and interestingness information derived from each known GIF.

10. The method of claim 9 , wherein said optimal playback setting corresponds to a version of the segment with a playback setting having a determined highest popularity score, said determined highest popularity score based on said application of the regression function.

11. The method of claim 1 , wherein the steps of the method are performed for multiple segments within the video file, wherein said method further comprises:
automatically selecting a predetermined number segments for GIF creation.

12. The method of claim 11 , wherein said selected segments satisfy a popularity score threshold.

13. The method of claim 11 , wherein said selected segments correspond to a number of segments being requested.

14. The method of claim 1 , further comprising:
determining a context of the animated GIF file;
causing communication, over the network, of said context to an advertisement platform to obtain digital advertisement content associated with said context; and
communicating said identified digital advertisement content with said animated GIF file to the user.

15. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a processor associated with a computing device, performs a method comprising:
receiving a request from a user for creation of an animated Graphics Interchange Format (GIF) file from a video file;
determining a segment within the video file, said segment determination comprising parsing the video file to identify transition frames within the video file, said segment comprising video frames of the video file existing between a pair of identified transition frames;
determining playback settings for the segment, each playback setting comprising a different frame sampling rate and time interval between each frame of the segment;
determining an n-dimensional feature vector for the segment, said feature vector determination comprising parsing the segment to identify information associated with motion, emotion and interestingness features of the segment, said feature vector based on the motion, emotion and interestingness information;
determining a popularity score for each playback setting based on the feature vector, said popularity score determination comprising determining an optimal playback setting for the segment from the playback settings; and
automatically creating the animated GIF file, said animated GIF file comprising said segment renderable at said optimal playback setting.

16. The non-transitory computer-readable storage medium of claim 15 , wherein said segment determination further comprising:
determining that said segment comprises a time length at or above a time threshold; and
re-parsing said segment via a multiple change point detection (MCPD) algorithm to identify additional transitional frames within the segment, wherein said segment is in accordance with said additional transitional frames.

17. The non-transitory computer-readable storage medium of claim 15 , wherein said playback settings determination further comprising:
determining a frame per second (FPS) value for the segment; and
determining a time interval between frames of the segment for each playback setting by multiplying a positive real number factor to the FPS value.

18. The non-transitory computer-readable storage medium of claim 15 , further comprising:
determining said motion information by analyzing attributes of the segment, said attributes comprising sha

Assignees

• Yahoo Holdings Inc

Inventors

• Song Yale
• Jaimes Alejandro

Classifications

• G11B27/031 Primary

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title

• G11B27/28

  by using information signals recorded by the same method as the main recording {(G11B27/22 takes precedence)} · CPC title