Discriminative Topics Modelling for Action Feature Selection and Recognition

Bregonzio, Matteo; Li, Jian; Gong, Shaogang; Xiang, Tao

doi:10.5244/c.24.8

Cited by 49 publications

(34 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bregonzio et al [4] achieve an accuracy of 96.75% which is a little lower than our method on the UCF feature films dataset. But Bregonzio et al [4] achieve an accuracy of 86.90% which is much lower than our 90.67% on the UCF Sport dataset.…”

Section: Experiments On the Ucf Feature Films Datasetcontrasting

confidence: 56%

“…[3] 93.17 -Bregonzio et al [4] -86.9 Sun et al [37] 94.0 -Yeffet and Wolf [51] 90.1 79.2 Wang et al [42] 92.1 85.6 Kovashka et al [14] 94.53 87.27 Le et al [19] 93.9 86.5 Wang et al [40] 94.2 88.2 Yuan et al [53] 95.49 87.33 method shows a higher performance. Bregonzio et al [4] achieve an accuracy of 96.75% which is a little lower than our method on the UCF feature films dataset. But Bregonzio et al [4] achieve an accuracy of 86.90% which is much lower than our 90.67% on the UCF Sport dataset.…”

Section: Experiments On the Ucf Feature Films Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Fusing $${\mathcal {R}}$$ R Features and Local Features with Context-Aware Kernels for Action Recognition

Yuan

et al. 2015

Int J Comput Vis

View full text Add to dashboard Cite

The performance of action recognition in video sequences depends significantly on the representation of actions and the similarity measurement between the representations. In this paper, we combine two kinds of features extracted from the spatio-temporal interest points with context-aware kernels for action recognition. For the action representation, local cuboid features extracted around interest points are very popular using a Bag of Visual Words (BOVW) model. Such representations, however, ignore potentially valuable information about the global spatio-temporal distribution of interest points. We propose a new global feature to capture the detailed geometrical distribution of interest points. It is calculated by using the 3D R transform which is defined as an extended 3D discrete Radon transform, followed by the application of a two-directional two-dimensional principal component analysis. For the similarity measurement, we model a video set as an optimized probabilistic hypergraph and propose a context-aware kernel to measure high order relationships among videos. The context-aware kernel is more robust to the noise and outliers in the data than the traditional context-free kernel which just considers the pairwise relationships between videos. The hyperedges of the hypergraph are constructed based on a learnt Mahalanobis distance metric. Any disturbing information from other classes is excluded from each hyperedge. Finally, a multiple kernel learning algorithm is designed by integrating the l 2 norm regularization into a linear SVM classifier to fuse the R feature and the BOVW representation for action recognition. Experimental results on several datasets demonstrate the effectiveness of the proposed approach for action recognition.

show abstract

Section: Experiments On the Ucf Feature Films Datasetcontrasting

confidence: 56%

Section: Experiments On the Ucf Feature Films Datasetmentioning

confidence: 99%

Fusing $${\mathcal {R}}$$ R Features and Local Features with Context-Aware Kernels for Action Recognition

Yuan

et al. 2015

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…In Jhuang et al (2007), feature subset selection by means of a support vector machine (SVM) is applied to position-invariant spatio-temporal features, resulting in a reduction of 24 times of the number of features. Spatio-temporal interest points are also used by Bregonzio et al (2010), where the global distribution information of interest points is exploited. Since the feature space dimension is very high, redundant features are eliminated.…”

Section: Human Action Recognitionmentioning

confidence: 99%

Optimizing human action recognition based on a cooperative coevolutionary algorithm

Chaaraoui

Flórez-Revuelta

2014

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Vision-based human action recognition is an essential part of human behavior analysis, which is currently in great demand due to its wide area of possible applications. In this paper, an optimization of a human action recognition method based on a cooperative coevolutionary algorithm is proposed. By means of coevolution, three different populations are evolved to obtain the best performing individuals with respect to instance, feature and parameter selection. The fitness function is based on the result of the human action recognition method. Using a multi-view silhouette-based pose representation and a weighted feature fusion scheme, an efficient feature is obtained, which takes into account multiple views and their relevance. Classification is performed by means of a bag of key poses, which represents the most characteristic pose representations, and matching of sequences of key poses. The performed experimentation indicates that not only a considerable performance gain is obtained outperforming the success rates of other state-of-the-art methods, but also the temporal and spatial performance of the algorithm is improved.

show abstract

“…The research trend in the field of action recognition has, recently, led to more robust techniques [13][14][15][16][17][18][19][20][21][22], which to some extent are applicable for action recognition in complex scenes. Action recognition in complex scenes is an extremely difficult task, due to several challenges, like background clutter, camera motion, occlusions and illumination variations.…”

Section: Human Action Recognitionmentioning

confidence: 99%

Selective spatio-temporal interest points

Chakraborty

Holte

Moeslund

et al. 2012

Computer Vision and Image Understanding

121

View full text Add to dashboard Cite

a b s t r a c tRecent progress in the field of human action recognition points towards the use of Spatio-Temporal Interest Points (STIPs) for local descriptor-based recognition strategies. In this paper, we present a novel approach for robust and selective STIP detection, by applying surround suppression combined with local and temporal constraints. This new method is significantly different from existing STIP detection techniques and improves the performance by detecting more repeatable, stable and distinctive STIPs for human actors, while suppressing unwanted background STIPs. For action representation we use a bagof-video words (BoV) model of local N-jet features to build a vocabulary of visual-words. To this end, we introduce a novel vocabulary building strategy by combining spatial pyramid and vocabulary compression techniques, resulting in improved performance and efficiency. Action class specific Support Vector Machine (SVM) classifiers are trained for categorization of human actions. A comprehensive set of experiments on popular benchmark datasets (KTH and Weizmann), more challenging datasets of complex scenes with background clutter and camera motion (CVC and CMU), movie and YouTube video clips (Hollywood 2 and YouTube), and complex scenes with multiple actors (MSR I and Multi-KTH), validates our approach and show state-of-the-art performance. Due to the unavailability of ground truth action annotation data for the Multi-KTH dataset, we introduce an actor specific spatio-temporal clustering of STIPs to address the problem of automatic action annotation of multiple simultaneous actors. Additionally, we perform cross-data action recognition by training on source datasets (KTH and Weizmann) and testing on completely different and more challenging target datasets (CVC, CMU, MSR I and Multi-KTH). This documents the robustness of our proposed approach in the realistic scenario, using separate training and test datasets, which in general has been a shortcoming in the performance evaluation of human action recognition techniques.

show abstract

Discriminative Topics Modelling for Action Feature Selection and Recognition

Cited by 49 publications

References 20 publications

Fusing $${\mathcal {R}}$$ R Features and Local Features with Context-Aware Kernels for Action Recognition

Fusing $${\mathcal {R}}$$ R Features and Local Features with Context-Aware Kernels for Action Recognition

Optimizing human action recognition based on a cooperative coevolutionary algorithm

Selective spatio-temporal interest points

Contact Info

Product

Resources

About