If you use data or code, please cite the following:
[1] Learning Human Activities and Object Affordances from RGB-D Videos, Hema S Koppula, Rudhir Gupta, Ashutosh Saxena. International Journal of Robotics Research (IJRR) 2013.
For CAD-120 dataset and more information refer to: http://pr.cs.cornell.edu/humanactivities/