Discriminative Hierarchical Rank Pooling for Activity Recognition

Basura Fernando; Peter Anderson; Marcus Hutter; Stephen Gould

CVPR 2016poster153 citations

Discriminative Hierarchical Rank Pooling for Activity Recognition

Basura Fernando, Peter Anderson, Marcus Hutter, Stephen Gould

Abstract

We present hierarchical rank pooling, a video sequence encoding method for activity recognition. It consists of a network of rank pooling functions which captures the dynamics of rich convolutional neural network features within a video sequence. By stacking non-linear feature functions and rank pooling over one another, we obtain a high capacity dynamic encoding mechanism, which is used for action recognition. We present a method for jointly learning the video representation and activity classifier parameters. Our method obtains state-of-the art results on three important activity recognition benchmarks: 76.7% on Hollywood2, 66.9% on HMDB51 and, 91.4% on UCF101.

BibTeX

@inproceedings{cvpr2016_discriminativehi,
  title = {Discriminative Hierarchical Rank Pooling for Activity Recognition},
  author = {Basura Fernando and Peter Anderson and Marcus Hutter and Stephen Gould},
  booktitle = {CVPR 2016},
  year = {2016}
}