Max-margin hidden conditional random fields for human action recognition
Yang Wang, Greg Mori · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2009
We present a new method for classification with structured latent variables. Our model is formulated using the max-margin formalism in the discriminative learning literature. We propose an efficient learning algorithm based on the cutting plane method and decomposed dual optimization. We apply our model to the problem of recognizing human actions from video sequences, where we model a human action as a global root template and a constellation of several “parts”. We show that our model outperforms another similar method that uses hidden conditional random fields, and is comparable to other state-of-the-art approaches. More importantly, our proposed work is quite general and can potentially be applied in a wide variety of vision problems that involve various complex, interdependent latent structures.
Cited by 155 works. doi:10.1109/cvpr.2009.5206709
Authors
References
- Convex Optimization
- Histograms of Oriented Gradients for Human Detection
- Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
- An Iterative Image Registration Technique with an Application to Stereo Vision
- A discriminatively trained, multiscale, deformable part model
- Pictorial Structures for Object Recognition
- What energy functions can be minimized via graph cuts?
- Recognizing human actions: A local SVM approach
- Behavior Recognition via Sparse Spatio-Temporal Features
- Recognizing human actions: a local SVM approach