Edge Video AI
We teach machines to watch live video.
Edge Video AI is a vision language model (VLM) that 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.
A research and product company in The Hague.
Edge Video AI, founded in 2019.
A vision language model for live video.
It watches, reads what's on screen and what's said, and says what is happening in the moment.
The market is all video.
Connected TV is where we start.
Design and content partners
- V-Shop
- 24x7 Movies
- MasterChef Méxicoon VIDAA
Our model
A model that watches first, then reasons.
Most AI reads text. Live video moves faster than text and carries more. Our vision language model sits on top: it watches the stream, follows every moment and knows when the ad break comes. A language model sits underneath to help it reason and to build apps when you ask.
Built for television
Edge ACR: our own content recognition on the TV, talking to the VLM.
Works on apps, HDMI and free-to-air. The picture never leaves the set.
Research
From Edge Research
Live enrichment: from frames to IAB categories
How a live channel becomes categories, keywords and brands, and why the expensive model only runs when the scene is new.
Technical report 03The VLM above the LLM
A layered architecture for live video: perception on top, language underneath, and instructions that turn into running apps.
Technical report 04Matching ads to moments
Holding programme context through the ad break, adding it to the existing ad request, and letting brands register their own ads.
Technical report 05Instructions as programs for live video
How a typed instruction, an answer shape and a validator become an app that runs over a live stream.
Our view
The missing layer.
Language models changed how software reads text. Video is still mostly a black box to the systems that sell ads against it and the shops that could sell from it. We think a model that can watch live video and say what is happening, in the moment it happens, is the missing layer.
Connected TV is where we start, because it is where live video, advertising and shopping already meet on one screen. The same model reads any live stream.
What is Edge Video AI?
- What is Edge Video AI?
- Edge Video AI is a vision language model (VLM) that 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.
- What is live enrichment?
- Live enrichment turns that into IAB categories, scene keywords and brands seen on screen.
- What is Edge ACR?
- Edge ACR is our own content recognition on the TV, talking to the vision language model (VLM). It works on apps, HDMI and free-to-air. The picture never leaves the set.
- What are the first two uses?
- The first two uses are ads and shopping. Autonomous Commerce for ads adds that context to the publisher's existing ad request, working alongside their playout and ad server. Shopping turns the moment into something you can buy.
- Where is Edge Video AI based?
- Edge Video AI is a research and product company in The Hague, founded in 2019.