Unit 5. Vision and Language

unit5.jpg

Description:

How do we recognize physical events in a dynamic visual scene? Andrei Barbu and his colleagues have developed a system that can generate a sentence like “The person to the right of the bin picked up the backpack” from a video clip portraying this action.

Alt text:
Still photo of a tall blue bin in center, with a man to the left standing with a folding chair and a man to the right with a backpack.
Caption:
How do we recognize physical events in a dynamic visual scene? Andrei Barbu and his colleagues have developed a system that can generate a sentence like “The person to the right of the bin picked up the backpack” from a video clip portraying this action.
Still photo of a tall blue bin in center, with a man to the left standing with a folding chair and a man to the right with a backpack.

Course Info

Learning Resource Types

theaters Other Video
theaters Lecture Videos
notes Lecture Notes
group_work Projects
co_present Instructor Insights