full transcript
"From the Ted Talk by Joseph Redmon: How computers learn to recognize objects instantly"

Unscramble the Blue Letters

This is a detector that we trained on 80 different classes in Microsoft's COCO dataset. It has all sorts of things like sopon and fork, bowl, common objects like that. It has a varitey of more etxioc things: aalnmis, cars, zebras, giraffes. And now we're going to do something fun. We're just going to go out into the audience and see what kind of things we can detect. Does anyone want a stuffed animal? There are some teddy bears out there. And we can turn down our threshold for detection a little bit, so we can find more of you guys out in the audcniee. Let's see if we can get these stop sings. We find some backpacks. Let's just zoom in a little bit. And this is great. And all of the processing is hpaepnnig in real time on the laptop.

Open Cloze

This is a detector that we trained on 80 different classes in Microsoft's COCO dataset. It has all sorts of things like _____ and fork, bowl, common objects like that. It has a _______ of more ______ things: _______, cars, zebras, giraffes. And now we're going to do something fun. We're just going to go out into the audience and see what kind of things we can detect. Does anyone want a stuffed animal? There are some teddy bears out there. And we can turn down our threshold for detection a little bit, so we can find more of you guys out in the ________. Let's see if we can get these stop _____. We find some backpacks. Let's just zoom in a little bit. And this is great. And all of the processing is _________ in real time on the laptop.

Solution

  1. exotic
  2. animals
  3. happening
  4. variety
  5. audience
  6. spoon
  7. signs

Original Text

This is a detector that we trained on 80 different classes in Microsoft's COCO dataset. It has all sorts of things like spoon and fork, bowl, common objects like that. It has a variety of more exotic things: animals, cars, zebras, giraffes. And now we're going to do something fun. We're just going to go out into the audience and see what kind of things we can detect. Does anyone want a stuffed animal? There are some teddy bears out there. And we can turn down our threshold for detection a little bit, so we can find more of you guys out in the audience. Let's see if we can get these stop signs. We find some backpacks. Let's just zoom in a little bit. And this is great. And all of the processing is happening in real time on the laptop.

ngrams of length 2

collocation frequency
object detection 6
computer vision 6
real time 3
detection system 3

Important Words

  1. animal
  2. animals
  3. audience
  4. backpacks
  5. bears
  6. bit
  7. bowl
  8. cars
  9. classes
  10. coco
  11. common
  12. dataset
  13. detect
  14. detection
  15. detector
  16. exotic
  17. find
  18. fork
  19. fun
  20. giraffes
  21. great
  22. guys
  23. happening
  24. kind
  25. laptop
  26. objects
  27. processing
  28. real
  29. signs
  30. sorts
  31. spoon
  32. stop
  33. stuffed
  34. teddy
  35. threshold
  36. time
  37. trained
  38. turn
  39. variety
  40. zebras
  41. zoom