Forecasting Hands and Objects in Future Frames

@inproceedings{Fan2017ForecastingHA,
  title={Forecasting Hands and Objects in Future Frames},
  author={Chenyou Fan and Jangwon Lee and Michael S. Ryoo},
  year={2017}
}
  • Chenyou Fan, Jangwon Lee, Michael S. Ryoo
  • Published 2017
This paper presents an approach to forecast future locations of human hands and objects. Given an image frame, the goal is to predict presence and location of hands and objects in the future frame (e.g., 5 seconds later), even when they are not visible in the current frame. The key idea is that (1) an intermediate representation of a convolutional object… CONTINUE READING