Bag-of-Words for Action Recognition using Random Projections - An Exploratory Study

Pau Agustí, V. Javier Traver, Filiberto Pla, Raúl Montoliu

2013

Abstract

During the last years, the bag-of-words (BoW) approach has become quite popular for representing actions from video sequences. While the BoW is conceptually very simple and practically effective, it suffers from some drawbacks. In particular, the quantization procedure behind the BoW usually relies on a computationally heavy k-means clustering. In this work we explore whether alternative approaches as simple as random projections, which are data agnostic, can represent a practical alternative. Results reveal that this randomized quantization offers an interesting computational-accuracy trade-off, because although recognition performance is not yet as high as with k-means, it is still competitive with an speed-up higher than one order of magnitude.

References

  1. Aggarwal, J. and Ryoo, M. (2011). Human activity analysis: A review. ACM CS.
  2. Aloise, D., Deshpande, A., Hansen, P., and Popat, P. (2009). NP-hardness of euclidean sum-of-squares clustering. ML.
  3. Bilinski, P. and Bremond, F. (2011). Evaluation of local descriptors for action recognition in videos. In ICCVS.
  4. Bingham, E. and Mannila, H. (2001). Random projection in dimensionality reduction: applications to image and text data. In KDD.
  5. Boutsidis, C., Zouzias, A., and Drineas, P. (2010). Random Projections for k-means Clustering. NIPS.
  6. Bregonzio, M., Xiang, T., and Gong, S. (2012). Fusing appearance and distribution information of interest points for action recognition. PM.
  7. Chakraborty, B., Holte, M. B., Moeslund, T. B., and Gonzlez, J. (2012). Selective spatio-temporal interest points. CVIU.
  8. Fern, X. Z. and Brodley, C. E. (2003). Random Projection for High Dimensional Data Clustering: A Cluster Ensemble Approach. In ICML.
  9. Gorelick, L., Blank, M., Shechtman, E., Irani, M., and Basri, R. (2007). Actions as Space-Time Shapes. tPAMI.
  10. Jain, A. K. (2010). Data clustering: 50 years beyond kmeans. PRL.
  11. Wu, X., Kumar, V., Ross Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G. J., Ng, A., Liu, B., Yu, P. S., Zhou, Z.-H., Steinbach, M., Hand, D. J., and Steinberg, D. (2007). Top 10 algorithms in data mining. KAIS.
Download


Paper Citation


in Harvard Style

Agustí P., Traver V., Pla F. and Montoliu R. (2013). Bag-of-Words for Action Recognition using Random Projections - An Exploratory Study . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 614-619. DOI: 10.5220/0004216906140619


in Bibtex Style

@conference{visapp13,
author={Pau Agustí and V. Javier Traver and Filiberto Pla and Raúl Montoliu},
title={Bag-of-Words for Action Recognition using Random Projections - An Exploratory Study},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={614-619},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004216906140619},
isbn={978-989-8565-47-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Bag-of-Words for Action Recognition using Random Projections - An Exploratory Study
SN - 978-989-8565-47-1
AU - Agustí P.
AU - Traver V.
AU - Pla F.
AU - Montoliu R.
PY - 2013
SP - 614
EP - 619
DO - 10.5220/0004216906140619