full transcript
From the Ted Talk by Supasorn Suwajanakorn: Fake videos of real people -- and how to spot them
Unscramble the Blue Letters
It turns out this problem is very cinnhgalelg, but the key trick is that we are going to analyze a lgare photo collection of the person beforehand. For George W. Bush, we can just search on Google, and from that, we are able to build an average model, an iterative, refined model to recover the expression in fine details, like ceasres and wrinkles. What's fascinating about this is that the photo ceioctolln can come from your typical photos. It doesn't really matter what expression you're making or where you took those photos. What mattres is that there are a lot of them. And we are still missing color here, so next, we develop a new blending technique that improves upon a single aevnigrag method and produces shrap facial textures and colors. And this can be done for any expression.
Open Cloze
It turns out this problem is very ___________, but the key trick is that we are going to analyze a _____ photo collection of the person beforehand. For George W. Bush, we can just search on Google, and from that, we are able to build an average model, an iterative, refined model to recover the expression in fine details, like _______ and wrinkles. What's fascinating about this is that the photo __________ can come from your typical photos. It doesn't really matter what expression you're making or where you took those photos. What _______ is that there are a lot of them. And we are still missing color here, so next, we develop a new blending technique that improves upon a single _________ method and produces _____ facial textures and colors. And this can be done for any expression.
Solution
- creases
- challenging
- large
- sharp
- collection
- matters
- averaging
Original Text
It turns out this problem is very challenging, but the key trick is that we are going to analyze a large photo collection of the person beforehand. For George W. Bush, we can just search on Google, and from that, we are able to build an average model, an iterative, refined model to recover the expression in fine details, like creases and wrinkles. What's fascinating about this is that the photo collection can come from your typical photos. It doesn't really matter what expression you're making or where you took those photos. What matters is that there are a lot of them. And we are still missing color here, so next, we develop a new blending technique that improves upon a single averaging method and produces sharp facial textures and colors. And this can be done for any expression.
Frequently Occurring Word Combinations
ngrams of length 2
collocation |
frequency |
output model |
2 |
photo collection |
2 |
Important Words
- analyze
- average
- averaging
- blending
- build
- bush
- challenging
- collection
- color
- colors
- creases
- details
- develop
- expression
- facial
- fascinating
- fine
- george
- google
- improves
- iterative
- key
- large
- lot
- making
- matter
- matters
- method
- missing
- model
- person
- photo
- photos
- problem
- produces
- recover
- refined
- search
- sharp
- single
- technique
- textures
- trick
- turns
- typical
- wrinkles