Local Trinary Patterns for human action recognition

Yeffet, Lahav; Wolf, Lior

doi:10.1109/iccv.2009.5459201

Cited by 279 publications

(166 citation statements)

References 21 publications

Supporting

Mentioning

160

Contrasting

Unclassified

Order By: Relevance

“…It collects a natural pool of actions featured in a wide range of scenes and viewpoints, and in unconstrained environments. The UCF sports database was tested in a leave-one-out manner, cycling each example in as a test video one at a time, following [18] [24] [22].…”

Section: Methodsmentioning

confidence: 99%

Multi-task Sparse Learning with Beta Process Prior for Action Recognition

Yuan

Tian

et al. 2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Multi-task Sparse Learning with Beta Process Prior for Action Recognition

Yuan

Tian

et al. 2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Yeffet and Wolf [36] 90.1 Laptev et al [37] 91.8 Schindler and Van Gool [30] 92.7 Kihl et al [38] 93.4 Baumann et al [39] 94.4 Proposed method 96.88 Figure 5(b) we compare our proposed method to the original Random Forest on the MNIST dataset with respect to the number of trees. Despite of some fluctuations our proposed method outperforms the standard implementation.…”

Section: Comparison To An Original Random Forest and To State-of-the-mentioning

confidence: 99%

Thresholding a Random Forest Classifier

Baumann

Ehlers

et al. 2014

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. The original Random Forest derives the final result with respect to the number of leaf nodes voted for the corresponding class. Each leaf node is treated equally and the class with the most number of votes wins. Certain leaf nodes in the topology have better classification accuracies and others often lead to a wrong decision. Also the performance of the forest for different classes differs due to uneven class proportions. In this work, a novel voting mechanism is introduced: each leaf node has an individual weight. The final decision is not determined by majority voting but rather by a linear combination of individual weights leading to a better and more robust decision. This method is inspired by the construction of a strong classifier using a linear combination of small rules of thumb (AdaBoost). Small fluctuations which are caused by the use of binary decision trees are better balanced. Experimental results on several datasets for object recognition and action recognition demonstrate that our method successfully improves the classification accuracy of the original Random Forest algorithm.

show abstract

“…This provides 240 instances of simple motions, such as bending and waving. Quantitative results are calculated using the popular nine-fold cross validation schema already used by [17], [19], [20].…”

Section: Validation Of Temporal Le Approachmentioning

confidence: 99%

Temporal Extension of Laplacian Eigenmaps for Unsupervised Dimensionality Reduction of Time Series

Lewandowski

Rincón

Makris

et al. 2010

2010 20th International Conference on Pattern Recognition

View full text Add to dashboard Cite

Abstract-A novel non-linear dimensionality reduction method, called Temporal Laplacian Eigenmaps, is introduced to process efficiently time series data. In this embedded-based approach, temporal information is intrinsic to the objective function, which produces description of low dimensional spaces with time coherence between data points. Since the proposed scheme also includes bidirectional mapping between data and embedded spaces and automatic tuning of key parameters, it offers the same benefits as mapping-based approaches. Experiments on a couple of computer vision applications demonstrate the superiority of the new approach to other dimensionality reduction method in term of accuracy. Moreover, its lower computational cost and generalisation abilities suggest it is scalable to larger datasets.

show abstract

Local Trinary Patterns for human action recognition

Cited by 279 publications

References 21 publications

Multi-task Sparse Learning with Beta Process Prior for Action Recognition

Multi-task Sparse Learning with Beta Process Prior for Action Recognition

Thresholding a Random Forest Classifier

Temporal Extension of Laplacian Eigenmaps for Unsupervised Dimensionality Reduction of Time Series

Contact Info

Product

Resources

About