Four media. Three verbs.

Our major theme is intelligence multimedia: deep learning and multimedia processing that let machines understand media, extract information from it and generate new media.

Understand

Classify, detect and recognise what the media contains.

Extract

Pull out information that is not written anywhere: a count, a transcript, a heart rate.

Generate

Produce new media: enhance it, separate it, summarise it.

Image & video
Audio & speech
Text & language
Multimodal

Not on the map: the group’s earlier work in signals & iot (18) and data & software (5).