Computer vision is a field where the goal is to enable machines to understand and use the visual content of images and videos in a similar manner to humans. In this talk Professor Zisserman will describe how machines are able to learn to recognise objects and actions from a temporal sequence of video frames, together with the audio and speech that accompanies them - an approach that is inspired by how infants may 'learn to see'. He will show applications of computer vision to image search, to recognising sign language (BSL), and to generating video descriptions for the visually impaired.
Attending the event
- The event is free to join
- Registration is recommended to attend in person otherwise availability cannot be guaranteed
- Live subtitles will be available in person and online.
Attending in person
- This lecture can be attended in person at the Royal Society
- Doors will open to the public at 6pm
- Registration is recommended if attending in person, otherwise availability cannot be guaranteed
- Travel and accessibility information
Attending live online
- The lecture will also be livestreamed here and on the Royal Society YouTube channel
- You can take part in the live Q&A which will be available on this page
- This event will be recorded (including the live Q&A) and the recording will be available on YouTube soon after the event
- The Royal Society has an acceptable use policy for all online events, and we expect our users to abide by these guidelines.
Enquiries: contact the Events team.