If you use the ImageNetShuffle ConvNet features please cite the following paper:

@INPROCEEDINGS{MettesICMR16,
  author = {Pascal Mettes and Dennis Koelma and Cees G. M. Snoek},
  title = {The ImageNet Shuffle: Reorganized Pre-training for Video Event Detection},
  booktitle = {Proceedings of the {ACM} International Conference on Multimedia Retrieval},
  year = {2016},
  address = {New York, USA}
}


The MBH features were generated with the aid of the Improved Trajectories executable from this page:
http://lear.inrialpes.fr/people/wang/improved_trajectories