# US 2020/0401813 A1 · Adaptive content classification of a video content item

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0401813 A1
- Document ID: US20200401813A1
- Status: Published application
- Kind: A1
- Application number: 16/905,728
- Filed: 2020-06-18
- Published: 2020-12-24
- Earliest claimed: 2019-06-21
- Assignees: Gfycat, Inc.
- Applicants: Gfycat, Inc.
- Inventors: Richard RABBAT; Ernestine FU
- Web page: https://patentgrep.com/patent/US20200401813A1

## CPC

- G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44)
- G06F 18/41: {Interactive pattern learning with a human teacher}
- G06T 11/00: Two-dimensional [2D] image generation
- G06V 20/49: {Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes}
- G06V 30/248: {involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" (G06V30/242 takes precedence)}
- G06V 30/2528: {Combination of methods, e.g. classifiers, working on the same input data}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

In a method for performing adaptive content classification of a video content item, frames of a video content item are analyzed at a sampling rate for a type of content, wherein the sampling rate dictates a frequency at which frames of the video content item are analyzed. Responsive to identifying content within at least one frame indicative of the type of content, the sampling rate of the frames is increased. Responsive to not identifying content within at least one frame indicative of the type of content, the sampling rate of the frames is decreased. It is determined whether the video content item includes the type of content based on the analyzing the frames.

## Claims

### Claim 1

A method for performing adaptive content classification of a video content item, the method comprising:
analyzing frames of a video content item at a sampling rate for a type of content, wherein the sampling rate dictates a frequency at which frames of the video content item are analyzed, the analyzing the frames comprising:
responsive to identifying content within at least one frame indicative of the type of content, increasing the sampling rate of the frames; and
responsive to not identifying content within at least one frame indicative of the type of content, decreasing the sampling rate of the frames; and
determining whether the video content item comprises the type of content based on the analyzing the frames.

### Claim 2 (depends on 1)

The method of claim 1, wherein the analyzing the frames comprises:
combining a plurality of frames of the video content item into a single image comprising a collage of frames for analysis.

### Claim 3 (depends on 2)

The method of claim 2, wherein the analyzing the frames comprises:
collectively analyzing the plurality of frames of the video content item of the single image.

### Claim 4 (depends on 2)

The method of claim 2, wherein the single image comprises a two by two collage of frames.

### Claim 5 (depends on 2)

The method of claim 2, wherein the single image comprises a three by three collage of frames.

### Claim 6 (depends on 1)

The method of claim 1, wherein the analyzing the frames comprises:
applying at least one classifier to the frames of the video content item, wherein the at least one classifier is configured to automatically identify a particular type of content.

### Claim 7 (depends on 1)

The method of claim 1, wherein the analyzing the frames comprises:
applying a plurality of classifiers to the frames of the video content item, wherein each classifier of the plurality of classifiers is configured to automatically identify a particular type of content.

### Claim 8 (depends on 7)

The method of claim 7, wherein the frames of the video content item are sequentially applied to the plurality of classifiers.

### Claim 9 (depends on 7)

The method of claim 7, wherein the frames of the video content item are concurrently applied to the plurality of classifiers.

### Claim 10 (depends on 1)

The method of claim 1, wherein the type of content comprises not safe for work (NSFW) content.

### Claim 11 (depends on 1)

The method of claim 1, wherein the determining whether the video content item comprises the type of content based on the analyzing the frames comprises:
provided a determination is made that it is inconclusive that the video content item comprises the type of content, forwarding the video content item for human review.

### Claim 12

A non-transitory computer readable storage medium having computer readable program code stored thereon for causing a computer system to perform a method for performing adaptive content classification of a video content item, the method comprising:
analyzing frames of a video content item at a sampling rate for a type of content, wherein the sampling rate dictates a frequency at which frames of the video content item are analyzed, the analyzing the frames comprising:
responsive to identifying content within at least one frame indicative of the type of content, increasing the sampling rate of the frames; and
responsive to not identifying content within at least one frame indicative of the type of content, decreasing the sampling rate of the frames; and
determining whether the video content item comprises the type of content based on the analyzing the frames.

### Claim 13 (depends on 12)

The non-transitory computer readable storage medium of claim 12, wherein the analyzing the frames comprises:
combining a plurality of frames of the video content item into a single image comprising a collage of frames for analysis.

### Claim 14 (depends on 13)

The non-transitory computer readable storage medium of claim 13, wherein the analyzing the frames comprises:
collectively analyzing the plurality of frames of the video content item of the single image.

### Claim 15 (depends on 12)

The non-transitory computer readable storage medium of claim 12, wherein the analyzing the frames comprises:
applying at least one classifier to the frames of the video content item, wherein the at least one classifier is configured to automatically identify a particular type of content.

### Claim 16 (depends on 12)

The non-transitory computer readable storage medium of claim 12, wherein the analyzing the frames comprises:
applying a plurality of classifiers to the frames of the video content item, wherein each classifier of the plurality of classifiers is configured to automatically identify a particular type of content.

### Claim 17 (depends on 12)

The non-transitory computer readable storage medium of claim 12, wherein the determining whether the video content item comprises the type of content based on the analyzing the frames comprises:
provided a determination is made that it is inconclusive that the video content item comprises the type of content, forwarding the video content item for human review.

### Claim 18

A computer system comprising:
a data storage unit; and
a processor coupled with the data storage unit, the processor configured to:
analyze frames of a video content item at a sampling rate for a type of content, wherein the sampling rate dictates a frequency at which frames of the video content item are analyzed, wherein analyzing the frames comprises:
increase the sampling rate of the frames responsive to identifying content within at least one frame indicative of the type of content; and
decrease the sampling rate of the frames responsive to not identifying content within at least one frame indicative of the type of content; and
determine whether the video content item comprises the type of content based on analysis of the frames.

### Claim 19 (depends on 18)

The computer system of claim 18, wherein the processor is further configured to:
combine a plurality of frames of the video content item into a single image comprising a collage of frames for analysis; and
collectively analyze the plurality of frames of the video content item of the single image.

### Claim 20 (depends on 18)

The computer system of claim 18, wherein the processor is further configured to:
apply at least one classifier to the frames of the video content item, wherein the at least one classifier is configured to automatically identify a particular type of content.
