Sparse Code Filtering for Action Pattern Mining

@inproceedings{Wang2016SparseCF,
  title={Sparse Code Filtering for Action Pattern Mining},
  author={Wei Wang and Yan Yan and Liqiang Nie and Luming Zhang and Stefan Winkler and N. Sebe},
  booktitle={ACCV},
  year={2016}
}
Action recognition has received increasing attention during the last decade. Various approaches have been proposed to encode the videos that contain actions, among which self-similarity matrices (SSMs) have shown very good performance by encoding the dynamics of the video. However, SSMs become sensitive when there is a very large view change. In this paper, we tackle the multi-view action recognition problem by proposing a sparse code filtering (SCF) framework which can mine the action patterns… 
Recurrent Convolutional Face Alignment
TLDR
By combining a convolutional neural network with a recurrent one the authors alleviate hand-crafted features, widely adopted in the literature and thus allowing the model to learn task-specific features, and further support the importance of learning a single end-to-end model for face alignment.

References

SHOWING 1-10 OF 34 REFERENCES
Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth Maps
TLDR
A new framework based on sparse coding and temporal pyramid matching (TPM) is proposed for depth-based human action recognition and shows that the proposed algorithm repeatedly achieves superior performance to the state of the art algorithms.
Multitask Linear Discriminant Analysis for View Invariant Action Recognition
TLDR
This work proposes multitask linear discriminant analysis (LDA), a novel multitask learning framework for multiview action recognition that allows for the sharing of discriminative SSM features among different views (i.e., tasks) by choosing an appropriate class indicator matrix.
Learning human actions via information maximization
  • Jingen Liu, M. Shah
  • Computer Science
    2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
TLDR
This paper presents a novel approach for automatically learning a compact and yet discriminative appearance-based human action model, and is the first to try the bag of video-words related approach on the multiview dataset.
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.
Recognizing Actions across Cameras by Exploring the Correlated Subspace
TLDR
This work proposes a novel SVM with a correlation regularizer which incorporates such ability into the design of the SVM, and explores the domain transfer ability of CCA in the correlation subspace, in which each dimension has a different capability in correlating source and target data.
Action recognition using rank-1 approximation of Joint Self-Similarity Volume
TLDR
The concept of Joint Self-Similarity Volume (Joint SSV) is introduced, and it is shown that by using a new optimized rank-1 tensor approximation of Joint SSV one can obtain compact low-dimensional descriptors that very accurately preserve the dynamics of the original system.
Latent Multitask Learning for View-Invariant Action Recognition
TLDR
An approach to view-invariant action recognition, where human poses and motions exhibit large variations across different camera viewpoints, which extends the standard multitask learning to allow identifying latent groupings of action views and discriminative action parts, along with joint learning of all tasks.
Incremental action recognition using feature-tree
TLDR
This work proposes a novel framework involving the feature- tree to index large scale motion features using Sphere/Rectangle-tree (SR-tree) and provides an effective way for practical incremental action recognition.
Cross-View Action Recognition from Temporal Self-similarities
TLDR
An action descriptor is developed that captures the structure of temporal similarities and dissimilarities within an action sequence that relies on weak geometric properties and combines them with machine learning for efficient cross-view action recognition.
...
...