full transcript

From the Ted Talk by Sougwen Chung: Why I draw with robots

Unscramble the Blue Letters

I was really inspired by Stanford researcher Fei-Fei Li, who said, "if we want to teach machines how to think, we need to first teach them how to see." It made me think of the past decade of my life in New York, and how I'd been all watched over by these surveillance cameras around the city. And I thought it would be really interesting if I could use them to teach my robots to see. So with this project, I thguoht about the gaze of the machine, and I began to think about vision as multidimensional, as views from somewhere. We collected video from publicly available camera feeds on the internet of people waklnig on the sidewalks, cars and taxis on the road, all kinds of urban movement. We trianed a vision atrlihgom on those feeds based on a tuncqeihe called "optical flow," to analyze the collective dsteniy, direction, dwell and velitcoy states of urban movement. Our sesytm extracted those states from the feeds as ptoiosianl data and became pads for my robotic units to draw on. Instead of a collaboration of one-to-one, we made a collaboration of many-to-many. By combining the vision of human and mhcinae in the city, we reimagined what a lcasnpade ptiniang could be.

Open Cloze

I was really inspired by Stanford researcher Fei-Fei Li, who said, "if we want to teach machines how to think, we need to first teach them how to see." It made me think of the past decade of my life in New York, and how I'd been all watched over by these surveillance cameras around the city. And I thought it would be really interesting if I could use them to teach my robots to see. So with this project, I _______ about the gaze of the machine, and I began to think about vision as multidimensional, as views from somewhere. We collected video from publicly available camera feeds on the internet of people _______ on the sidewalks, cars and taxis on the road, all kinds of urban movement. We _______ a vision _________ on those feeds based on a _________ called "optical flow," to analyze the collective _______, direction, dwell and ________ states of urban movement. Our ______ extracted those states from the feeds as __________ data and became pads for my robotic units to draw on. Instead of a collaboration of one-to-one, we made a collaboration of many-to-many. By combining the vision of human and _______ in the city, we reimagined what a _________ ________ could be.

Solution

  1. positional
  2. painting
  3. system
  4. technique
  5. algorithm
  6. velocity
  7. trained
  8. walking
  9. landscape
  10. thought
  11. machine
  12. density

Original Text

I was really inspired by Stanford researcher Fei-Fei Li, who said, "if we want to teach machines how to think, we need to first teach them how to see." It made me think of the past decade of my life in New York, and how I'd been all watched over by these surveillance cameras around the city. And I thought it would be really interesting if I could use them to teach my robots to see. So with this project, I thought about the gaze of the machine, and I began to think about vision as multidimensional, as views from somewhere. We collected video from publicly available camera feeds on the internet of people walking on the sidewalks, cars and taxis on the road, all kinds of urban movement. We trained a vision algorithm on those feeds based on a technique called "optical flow," to analyze the collective density, direction, dwell and velocity states of urban movement. Our system extracted those states from the feeds as positional data and became pads for my robotic units to draw on. Instead of a collaboration of one-to-one, we made a collaboration of many-to-many. By combining the vision of human and machine in the city, we reimagined what a landscape painting could be.

Frequently Occurring Word Combinations

ngrams of length 2

collocation frequency
work traditionally 2
human creativity 2
robotic arm 2
real time 2
york city 2
neural net 2
human hand 2
urban movement 2
interhuman collaboration 2

Important Words

  1. algorithm
  2. analyze
  3. based
  4. began
  5. called
  6. camera
  7. cameras
  8. cars
  9. city
  10. collaboration
  11. collected
  12. collective
  13. combining
  14. data
  15. decade
  16. density
  17. direction
  18. draw
  19. dwell
  20. extracted
  21. feeds
  22. flow
  23. gaze
  24. human
  25. inspired
  26. interesting
  27. internet
  28. kinds
  29. landscape
  30. li
  31. life
  32. machine
  33. machines
  34. movement
  35. multidimensional
  36. pads
  37. painting
  38. people
  39. positional
  40. project
  41. publicly
  42. reimagined
  43. researcher
  44. road
  45. robotic
  46. robots
  47. sidewalks
  48. stanford
  49. states
  50. surveillance
  51. system
  52. taxis
  53. teach
  54. technique
  55. thought
  56. trained
  57. units
  58. urban
  59. velocity
  60. video
  61. views
  62. vision
  63. walking
  64. watched
  65. york