Science Alert June 14, 2018
Researchers in Germany wanted to see if a program could list a sequence of actions up to five minutes into the future based on watching the first few steps of an activity. They trained software to guess what a chef would do next by showing it a number of videos of people making breakfast or a salad. They then showed the program a completely new video of another person preparing a similar meal, and watched how it guessed upcoming steps and their respective duration. One approach anticipated future actions and reflected before anticipating again, and another that built a matrix in one hit before crunching the probabilities. The deeper they looked into the future, the more mistakes they made. They discovered their trained program could correctly predict an action and its duration 3 minutes in the future roughly 15 percent of the time. Their work will be presented at this year’s IEEE Conference on Computer Vision and Pattern Recognition in Salt Lake City…read more.