Is it possible to customize the Video Moderation API to my needs?

There is no one-size-fits-all solution with Video Moderation. Expectations will vary between countries, cultures and applications.

This is why we have worked to make our API endpoints and models flexible and suitable to most needs.

You choose the models you want to apply

As you may know, we have multiple moderation models available. When you perform a request to the API, you get to choose what models to apply and how each model is used to then decide if a video should be approved, rejected or reviewed. See our Model Reference to learn more about each model output.

Each model returns fine-grained results

Our models do not return simple binary classifications (such as 'nudity' or 'no nudity'). They send you more information so that you can make a fine-grained decision on how to handle each case.

The Nudity Detection, for instance, will tell you what level of nudity it has encountered for each frame of the video. When faced with suggestive content, we tell you exactly what the video contains, so that you can take appropriate action - or simply accept the video.

In other words, you don't need to worry about how videos get handled when they are border-line nudity.

This applies to Nudity Detection but also to all the other available models.

Each moderation category is associated with a score

A score between 0 and 1 is returned for each moderation category and for each frame of the video. This value reflects the model’s confidence. A score closer to 1 indicates that the frame has a higher probability of containing what the model is looking for.

With these scores associated with each frame, you can define thresholds to help you make a decision about the video you submitted. If you need some help to decide which thresholds would match your needs, please reach out.

You can create custom disallow lists

Disallow Lists can help you blacklist some specific videos or clips by fingerprinting them and preventing them from (re)appearing on your site or app. This is useful to make sure known copyrighted videos, illegal videos, or previously removed videos do not get re-uploaded to your properties, either in full or in part.

Once you add a video to the list, any other video that has a common sequence with this video will be detected.

The steps to setup and use a Video Disallow List are the following:

Create a Video Disallow List from your dashboard.
Add videos to the disallow list (through the dashboard or through the API).
Check new and existing videos against the disallow list.

To get more information on how to use Video Disallow Lists, check the documentation.

And send misclassified frames to the feedback API

Our models have been trained to achieve best-in-class accuracy, yet you might want to report video frames you believe were misclassified. To do that, you can extract the frame and submit it as an image to the Feedback API. Submitted images are used to improve the models on a continuous basis, and submitting them will not impact your billing.

See how to report misclassified images for the list of models and classes you can report.

Need more?

That said, if you believe you need more customization than provided out-of-the-box, for instance with new detection capacities or custom decision filters, please get in touch.