Abstract
This paper presents an exemplar-based approach to detecting and localizing human actions, such as running, cycling, and swinging, in realistic videos with dynamic backgrounds. We show that such activities can be compactly represented as time series of a few snapshots of human-body parts in their most discriminative postures, relative to other activity classes. This enables our approach to efficiently store multiple diverse exemplars per activity class, and quickly retrieve exemplars that best match the query by aligning their short time-series representations. Given a set of example videos of all activity classes, we extract multiscale regions from all their frames, and then learn a sparse dictionary of most discriminative regions. The Viterbi algorithm is then used to track detections of the learned codewords across frames of each video, resulting in their compact time-series representations. Dictionary learning is cast within the large-margin framework, wherein we study the effects of ℓ1 and ℓ2 regularization on the sparseness of the resulting dictionaries. Our experiments demonstrate robustness and scalability of our approach on challenging YouTube videos.
Chapter PDF
Similar content being viewed by others
References
Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)
Niebles, J.C., Han, B., Ferencz, A., Fei-Fei, L.: Extracting moving people from internet videos. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 527–540. Springer, Heidelberg (2008)
Yao, B., Zhu, S.C.: Learning deformable action templates from cluttered videos. In: ICCV (2009)
Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos “in the wild”. In: CVPR (2009)
Fanti, C., Zelnik-Manor, L., Perona, P.: Hybrid models for human motion recognition. In: CVPR (2005)
Bissacco, A., Yang, M.H., Soatto, S.: Detecting humans via their pose. In: NIPS (2007)
Ning, H., Xu, W., Gong, Y., Huang, T.: Discriminative learning of visual words for 3d human pose estimation. In: CVPR (2008)
Ke, Y., Sukthankar, R., Hebert, M.: Event detection in crowded videos. In: ICCV (2007)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In. CVPR, pp. 886–893 (2005)
Lin, Z., Davis, L.S.: A pose-invariant descriptor for human detection and segmentation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 423–436. Springer, Heidelberg (2008)
Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)
Lin, Z., Jiang, Z., Davis, L.S.: Recognizing actions by shape-motion prototype trees. In: ICCV (2009)
Liu, J., Shah, M.: Learning human actions via information maximization. In: CVPR (2008)
Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. IEEE TPAMI 29, 2247–2253 (2007)
Brendel, W., Todorovic, S.: Video object segmentation by tracking regions. In: ICCV (2009)
Frome, A., Singer, Y., Sha, F., Malik, J.: Learning globally-consistent local distance functions for shape-based image retrieval and classification. In: ICCV (2007)
Gilad-Bachrach, R., Navot, A., Tishby, N.: Margin based feature selection – theory and algorithms. In: ICML, vol. 43 (2004)
Vedaldi, A., Soatto, S.: Quick shift and kernel methods for mode seeking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 705–718. Springer, Heidelberg (2008)
Schueldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local SVM approach. In: ICPR (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
1 Electronic Supplementary Material
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Brendel, W., Todorovic, S. (2010). Activities as Time Series of Human Postures. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6312. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15552-9_52
Download citation
DOI: https://doi.org/10.1007/978-3-642-15552-9_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15551-2
Online ISBN: 978-3-642-15552-9
eBook Packages: Computer ScienceComputer Science (R0)