Abstract
“Actions in the wild” is the term given to examples of human motion that are performed in natural settings, such as those harvested from movies [10] or the Internet [9]. State-of-the-art approaches in this domain are orders of magnitude lower than in more contrived settings. One of the primary reasons being the huge variability within each action class. We propose to tackle recognition in the wild by automatically breaking complex action categories into multiple modes/group, and training a separate classifier for each mode. This is achieved using RANSAC which identifies and separates the modes while rejecting outliers. We employ a novel reweighting scheme within the RANSAC procedure to iteratively reweight training examples, ensuring their inclusion in the final classification model. Our results demonstrate the validity of the approach, and for classes which exhibit multi-modality, we achieve in excess of double the performance over approaches that assume single modality.
This work is supported by the EU FP7 Project Dicta-Sign (FP7/2007-2013) under grant agreement no 231135, and the EPSRC project Making Sense (EP/H023135/1).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: VS-PETS, pp. 65–72 (2005)
Fischler, M.A., Bolles, R.C.: Ransac: A paradigm for model fitting with applications to image analysis and automated cartography. Comms. of the ACM 24(6), 381–395 (1981)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: Vitányi, P.M.B. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 23–37. Springer, Heidelberg (1995)
Gilbert, A., Illingworth, J., Bowden, R.: Action recognition using mined hierarchical compound features. PAMI 99(PrePrints) (2010)
Han, D., Bo, L., Sminchisescu, C.: Selection and context for action recognition. In: ICCV, pp. 1–8 (2009)
Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR, pp. 1–8 (2008)
Laptev, I., Perez, P.: Retrieving actions in movies. In: ICCV, pp. 1–8 (2007)
Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos ”in the wild”. In: CVPR, pp. 1–8 (2009)
Liu, J., Shah, M.: Learning human actions via information maximization. In: CVPR, pp. 1–8 (2008)
Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR, pp. 1–8 (2009)
Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local SVM approach. In: ICPR, pp. 32–36 (2004)
Szepannek, G., Schiffner, J., Wilson, J., Weihs, C.: Local modelling in classification. In: Perner, P. (ed.) ICDM 2008. LNCS (LNAI), vol. 5077, pp. 153–164. Springer, Heidelberg (2008)
Ullah, M.M., Parizi, S.N., Laptev, I.: Improving bag-of-features action recognition with non-local cues. In: BMVC, pp. 95.1–95.11 (2010)
Urtasun, R., Darrell, T.: Sparse probabilistic regression for activity-independent human pose inference. In: CVPR (2008)
Zhang, H., Berg, A.C., Maire, M., Malik, J.: Svm-knn: Discriminative nearest neighbor classification for visual category recognition. In: CVPR, pp. 2126–2136 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Oshin, O., Gilbert, A., Bowden, R. (2011). There Is More Than One Way to Get Out of a Car: Automatic Mode Finding for Action Recognition in the Wild. In: Vitrià, J., Sanches, J.M., Hernández, M. (eds) Pattern Recognition and Image Analysis. IbPRIA 2011. Lecture Notes in Computer Science, vol 6669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21257-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-21257-4_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21256-7
Online ISBN: 978-3-642-21257-4
eBook Packages: Computer ScienceComputer Science (R0)