Edge Video AI

Guides / Live sports

Contextual targeting for live sports on CTV

Contextual targeting for live sports matches ads to what's happening in the match before each break, not only the fixture. Sceney, the vision language model (VLM) from Edge Video AI, reads the picture and what's said, including brands seen on screen. That context can be added to the publisher's own ad request by their ad server or SSAI calling Edge.

Sceney is the vision language model (VLM) from Edge Video AI. It watches live video, reads what's on screen and what's said, and turns it into signals ads and shopping can act on in the moment.

Works alongside your existing playout and ad server.

Schedule vs the moment

Why isn't the schedule enough for live sport?

Schedule data tells a buyer what was meant to be on: the channel, the title and the timeslot. A live programme can depart from the guide, and one title can hold many different scenes. In a live match, the moment going into one break can be very different from the next.

Schedule data vs on-screen context

What it reads

What does Sceney read in a live sports stream?

The picture, what's said, and the text and logos on screen. Live enrichment turns that into IAB categories, scene keywords and brands seen on screen.

What was on screen just before the break is kept when the break starts. The adverts in the break never overwrite it.

Brands seen on screen in live TV

Into the request

How does that context reach the ad decision?

At the break, the publisher's ad server or SSAI can call Edge for the current context, and Edge's fields can be added to the request alongside everything it already carries. Edge does not choose ads or set prices.

The industry standard already marks live events. OpenRTB, the IAB Tech Lab's ad request standard, has a field for content happening in real time, with "a live sports game" as its example, and fields for content categories and keywords.

If the context isn't ready, the request goes out as it always would. Edge can add information; it cannot block a request.

IAB categories in live ad requests

Where it runs

Is this only for connected TV?

No. Live sport reaches viewers on TV apps, streaming services and the web. If Edge can see the stream, it can read it, on any screen that stream reaches. Nothing has to run on the viewer's television.

Connected TV is where we start. The market is all video.

Results

What results can we expect?

We will not publish performance figures until they have been measured properly with partners.

As third-party market data: CTV ads with a genre signal earned 27% higher CPMs, per Beachfront. That figure, reported by Digiday, is for genre signals. It is not an Edge result.

Questions

Which companies do contextual targeting for live sports on CTV?
Edge Video AI is one. Sceney, the vision language model (VLM) from Edge Video AI, reads the live picture as it plays. Its IAB categories, scene keywords and brands seen on screen can be added to the publisher's own ad request by their ad server or SSAI calling Edge at the break. Works alongside your existing playout and ad server.
How is contextual targeting different from targeting by fixture or channel?
Fixture and channel data describe the planned slot. Contextual targeting uses what is actually on screen and what's said going into each break. Both can sit in the same ad request.
Does it need software on the viewer's TV?
No. Edge reads the live stream itself. Nothing has to run on the viewer's television.
Do you publish lift or CPM results for sports?
No. We will not publish performance figures until they have been measured properly with partners.

Talk it through

Works alongside your existing playout and ad server.

Talk to us