Boosting VLAD with double assignment using deep features for action recognition in videos

@article{Duta2016BoostingVW,
  title={Boosting VLAD with double assignment using deep features for action recognition in videos},
  author={Ionut C. Duta and Tuan Anh Nguyen and Kiyoharu Aizawa and Bogdan Ionescu and Nicu Sebe},
  journal={2016 23rd International Conference on Pattern Recognition (ICPR)},
  year={2016},
  pages={2210-2215}
}
The encoding method is an important factor for an action recognition pipeline. One of the key points for the encoding method is the assignment step. A very widely used super-vector encoding method is the vector of locally aggregated descriptors (VLAD), with very competitive results in many tasks. However, it considers only hard assignment and the criteria… CONTINUE READING