Title
Recognizing Realistic Actions From Videos ́In The Wild
Abstract
In this paper, we present a systematic framework for re-cognizing 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 se-mantically 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. © 2009 IEEE.
Publication Date
1-1-2009
Publication Title
2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Number of Pages
1996-2003
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPRW.2009.5206744
Copyright Status
Unknown
Socpus ID
70450203660 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/70450203660
STARS Citation
Liu, Jingen; Luo, Jiebo; and Shah, Mubarak, "Recognizing Realistic Actions From Videos ́In The Wild" (2009). Scopus Export 2000s. 12718.
https://stars.library.ucf.edu/scopus2000/12718