Learning Zeroth Class Dictionary for Human Action Recognition

@inproceedings{Cai2017LearningZC,
  title={Learning Zeroth Class Dictionary for Human Action Recognition},
  author={Jia-xin Cai and Xin Tang and Lifang Zhang and Guo-Can Feng},
  booktitle={CCCV},
  year={2017}
}
In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected discriminative frames and the second-phase dictionary is built for recognition using reconstruction errors of the first-phase dictionary as input features. We propose a “zeroth class” trick for detecting undiscriminating frames of the test video and eliminating them before voting on the… 
3 Citations

Figures, Tables, and Topics from this paper

Human action recognition: a framework of statistical weighted segmentation and rank correlation-based selection
TLDR
This article considers the problems related to multiple human detection and classification using novel statistical weighted segmentation and rank correlation-based feature selection approach and proves the significance of proposed compared to other techniques.
HUMAN ACTIVITY DETECTION AND ACTION RECOGNITION IN VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS
TLDR
A novel approach of feature extraction from video sequence by combining Scale Invariant Feature Transform and optical flow computation are used where shape, gradient and orientation features are also incorporated for robust feature formulation.
Human Action Recognition using Contour History Images and Neural Networks Classifier
1,2,3 Higher Institute for Applied Sciences and Technology

References

SHOWING 1-10 OF 42 REFERENCES
Learning Pose Dictionary for Human Action Recognition
We proposed a framework for human action recognition by learning pose dictionary as the human appearance representation. At first, the shape based pose feature is constructed based on the contour
Supervised class-specific dictionary learning for sparse modeling in action recognition
TLDR
A new supervised classification method based on a modified sparse model which incorporates the similarity constrained term and the dictionary incoherence term for classification and adopts a specific dictionary for each action class.
Learning Sparse Representations for Human Action Recognition
  • T. Guha, R. Ward
  • Computer Science, Medicine
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2012
TLDR
This paper explores the effectiveness of sparse representations obtained by learning a set of overcomplete basis (dictionary) in the context of action recognition in videos and presents the idea of a new local spatio-temporal feature that is distinctive, scale invariant, and fast to compute.
Sparse representation based action and gesture recognition
TLDR
The authors' model is modelled as a simple concatenation of features computed for each action or gesture class from the training data, and test data is classified by finding sparse representation of the test video features over this dictionary.
Action recognition by learning discriminative key poses
TLDR
This paper proposes a novel approach to pose-based human action recognition that first extracts a scale invariant contour-based pose feature from silhouettes, then clusters the features in order to build a set of prototypical key poses and learns weights that favor distinctive key poses.
Sparse dictionary-based representation and recognition of action attributes
TLDR
This work unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes and proposes a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function.
Sparse coding-based spatiotemporal saliency for action recognition
TLDR
This paper proposes to measure the spatiotemporal saliency of patches using Shannon's self-information entropy, where a patch's saliency is determined by information variation in the contents of the patch's spatiotmporal neighborhood.
Learning low-rank and discriminative dictionary for image classification
TLDR
The proposed discriminative dictionary learning with low-rank regularization (D2L2R2) approach is evaluated on four face and digit image datasets in comparison with existing representative dictionary learning and classification algorithms and demonstrates the superiority of the approach.
Temporal key poses for human action recognition
TLDR
This approach integrates the advantages of human action recognition in static images using action key poses and motion based approaches using the variants of Motion History Images (MHI) and Motion Energy Images (MEI) to extract a new representation of temporal key poses.
Multi-view human action recognition using 2D motion templates based on MHIs and their HOG description
TLDR
This is the first report of results on the MuHAVi-uncut dataset having a large number of action categories and a large set of camera-views with noisy silhouettes which can be used by future workers as a baseline to improve on and compares well to similar state-of-the-art approaches.
...
1
2
3
4
5
...