Feature sampling and partitioning for visual vocabulary generation on large action classification datasets

29 May 2014  ·  Michael Sapienza, Fabio Cuzzolin, Philip H. S. Torr ·

The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies. State-of-the-art human action classification in challenging video data is currently based on a bag-of-visual-words pipeline in which space-time features are aggregated globally to form a histogram. The strategies chosen to sample features and construct a visual vocabulary are critical to performance, in fact often dominating performance. In this work we provide a critical evaluation of various approaches to building a vocabulary and show that good practises do have a significant impact. By subsampling and partitioning features strategically, we are able to achieve state-of-the-art results on 5 major action recognition datasets using relatively small visual vocabularies.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here