Create AI CM:nsfw task

curl --request POST \
  --url 'https://api.gcore.com/streaming/ai/tasks#cm_nsfw' \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "https://demo-files.gvideo.io/ai_demo_subtitles_nudity_detection.mp4",
  "task_name": "content-moderation",
  "category": "nsfw"
}
'

{
  "task_id": "aafe70c6-0000-0000-0000-327b65f7670f"
}

Create AI CM:nsfw task

This algorithm allows to quickly detect inappropriate content, determining that the content is NSFW (“Not Safe For Work”) or normal. Generic info about all capabilities and limits see in the generic “Content Moderation” method.

What is “Not Safe For Work”?

The algorithm has recognized inappropriate content in a video and it might not be suitable to view in public places. The solution provides its confidence level (in percentage) of how sure it is that the content is NSFW, or it most likely does not contain any sexual or similar content.

Different to soft-nudity-detection and hard-nudity-detection, this model will only check for sensitive material that can be considered not-safe-for-work.

AI Content Moderation: NSFW detection visual example

How to use?

Frames within the specified video are analyzed.

Response will contain only frames for which the class nsfw is detected with a confidence of more than 50%.

Example of detected NSFW:

{
  "nsfw_detected": true,
  "detection_results": [ "nsfw" ],
  "frames": [
      {
          "label": "nsfw",
          "confidence": 0.93,
          "frame_number": 1
      },..
  ]
}

Example of a response without detecting inappropriate content:

{
  "nsfw_detected": false,
  "detection_results": [],
  "frames": []
}

Please note that the API only provides a set of data (json) about the objects found, so no video is generated. The demo video video (above ^) was specially created based on json from the API for visual demonstration and better perception of the possibilities.

POST

streaming

tasks#cm_nsfw

Create AI CM:nsfw task

curl --request POST \
  --url 'https://api.gcore.com/streaming/ai/tasks#cm_nsfw' \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "https://demo-files.gvideo.io/ai_demo_subtitles_nudity_detection.mp4",
  "task_name": "content-moderation",
  "category": "nsfw"
}
'

{
  "task_id": "aafe70c6-0000-0000-0000-327b65f7670f"
}

Authorizations

Authorization

string

header

required

API key for authentication. Make sure to include the word apikey, followed by a single space and then your token. Example: apikey 1234$abcdef

Body

application/json

task_name

enum<string>

required

Name of the task to be performed

Available options:

content-moderation

url

string

required

URL to the MP4 file to analyse. File must be publicly accessible via HTTP/HTTPS.

Response

Response returns ID of the created AI task. Using this AI task ID, you can check the status and get the video processing result. Look at GET /ai/results method.

task_id

string<uuid>

required

ID of the created AI task, from which you can get the execution result

Create AI ASR task Create AI CM:hard_nudity task

⌘I

Overview

IAM

CDN

Managed DNS

Cloud

DDoS Protection

FastEdge

WAAP

Streaming

Object Storage

Resellers

Create AI CM:nsfw task

Authorizations

Body

Response