Action recognition by learning mid-level motion features
Alireza Fathi, Greg Mori · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2008
This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches or large-scale features describing the entire human figure. We develop a method constructing mid-level motion features which are built from low-level optical flow information. These features are focused on local regions of the image sequence and are created using a variant of AdaBoost. These features are tuned to discriminate between different classes of action, and are efficient to compute at run-time. A battery of classifiers based on these mid-level features is created and used to classify input sequences. State-of-the-art results are presented on a variety of standard datasets.
Cited by 458 works. doi:10.1109/cvpr.2008.4587735
Authors
References
- Gradient-based learning applied to document recognition
- Histograms of Oriented Gradients for Human Detection
- An Iterative Image Registration Technique with an Application to Stereo Vision
- Improved boosting algorithms using confidence-rated predictions
- Solving Multiclass Learning Problems via Error-Correcting Output Codes
- Robust Object Recognition with Cortex-Like Mechanisms
- Robust real-time object detection.
- GradientBased Learning Applied to Document Recognition
- Recognizing human actions: A local SVM approach
- Behavior Recognition via Sparse Spatio-Temporal Features