Seungryul Beak

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
Existing work for action recognition from depth sequences focus on modeling the dynamics of various actions. In this paper, we tackle the problem of 24 hours-monitoring patient actions in a ward, where temporal movements can be significant or subtle, and their relative positions to scene layout and body postures become important cues, such as " lying on the(More)
  • 1