Recognizing realistic actions from videos “in the wild”
Authors:
Top Cited Papers
- 1 June 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1996-2003
Abstract
In this paper, we present a systematic framework for recognizing realistic actions from videos “in the wild”. Such unconstrained videos are abundant in personal collections as well as on the Web. Recognizing action from such videos has not been addressed extensively, primarily due to the tremendous variations that result from camera motion, background clutter, changes in object appearance, and scale, etc. The main challenge is how to extract reliable and informative features from the unconstrained videos. We extract both motion and static features from the videos. Since the raw features of both types are dense yet noisy, we propose strategies to prune these features. We use motion statistics to acquire stable motion features and clean static features. Furthermore, PageRank is used to mine the most informative static features. In order to further construct compact yet discriminative visual vocabularies, a divisive information-theoretic algorithm is employed to group semantically related features. Finally, AdaBoost is chosen to integrate all the heterogeneous yet complementary features for recognition. We have tested the framework on the KTH dataset and our own dataset consisting of 11 categories of actions collected from YouTube and personal videos, and have obtained impressive results for action recognition and action localization.Keywords
This publication has 15 references indexed in Scilit:
- Learning realistic human actions from movies2008
- Action recognition with motion-appearance vocabulary forest2008
- A Hierarchical Model of Shape and Appearance for Human Action Classification2007
- Behavior Recognition via Sparse Spatio-Temporal Features2006
- A Comparison of Affine Region DetectorsInternational Journal of Computer Vision, 2005
- Hybrid Models for Human Motion Recognition2005
- A spectral technique for correspondence problems using pairwise constraints2005
- Space-time interest points2003
- 10.1162/153244303322753661Applied Physics Letters, 2000
- 10.1162/153244303322753616Applied Physics Letters, 2000