Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning

Paoletti, Giancarlo; Cavazza, Jacopo; Beyan, Çiğdem; Bue, Alessio Del

doi:10.1109/icpr48806.2021.9412060

Cited by 31 publications

(20 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 Use the roulette wheel selection method to choose a cluster as c * Recalculate the number of cluster by k = k − 1 effectiveness, we compared the proposed method with nonautomatic methods (having prior knowledge of the number of clusters) including KM (k-means), SC (spectral clustering), ENSC (elastic net subspace clustering), SSC (Sparse Subspace Clustering) [35] and GMM (Gaussian mixture model) and automatic methods including DBSCAN, MS (Mean-shift clustering), PSO [51], HPGMK [8], and MOPGMGT [36].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Flexible Multi-Objective Particle Swarm Optimization Clustering with Game Theory to Address Human Activity Recognition Fully Unsupervised

Hadikhani¹,

Lai²,

Ong³

2022

Preprint

View full text Add to dashboard Cite

Most research in human activity recognition is supervised, while non-supervised approaches are not completely unsupervised. In this paper, we provide a novel flexible multi-objective particle swarm optimization (PSO) clustering method based on game theory (FMOPG) to discover human activities fully unsupervised. Unlike conventional clustering methods that estimate the number of clusters and are very time-consuming and inaccurate, an incremental technique is introduced which makes the proposed method flexible in dealing with the number of clusters. Using this technique, clusters that have a better connectedness and good separation from other clusters are gradually selected. To improve the convergence speed of PSO in achieving the best solution and dealing with spherical shape clusters, updating of particles' velocity is modified using the concept of mean-shift vector. To solve multi-objective optimization problems, Nash equilibrium in game theory is used to select the optimal solution on the pareto front. Gaussian mutation is also employed on the pareto front to generate diverse solutions and create a balance between exploitation and exploration. The proposed method is compared with state-of-the-art methods on five challenging datasets. FMOPG has improved clustering accuracy by 3.65% compared to automated methods. Moreover, the incremental technique has improved the clustering time by 71.18%.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Noisy data and outliers were not considered. Paoletti et al [35] used subspace clustering to discover human activities. To reduce the number of redundant frames, they introduced a trim method.…”

Section: Human Activity Recognition and Discoverymentioning

confidence: 99%

Flexible Multi-Objective Particle Swarm Optimization Clustering with Game Theory to Address Human Activity Recognition Fully Unsupervised

Hadikhani¹,

Lai²,

Ong³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The stop criteria was based on the number of iteration. The performance of the proposed method was compared with the four automatic clustering including PSO [40], HPGMK [2], MOPSO (multi-objective PSO) [41], MOPGM (multi-objective PSO with Gaussian mutation) and four non-automatic clustering (with known number of clusters) algorithms contain KM (k-means), SC (spectral clustering), ENSC (elastic net subspace clustering), and SSC (Sparse Subspace Clustering) [3]. We have used KM, SC as the baseline approach and PSO, MOPSO and MOPGM have been picked for comparison because our proposed method is based on these algorithms.…”

Section: B Setupmentioning

confidence: 99%

Human Activity Discovery with Automatic Multi-objective Particle Swarm Optimization Clustering with Gaussian Mutation and Game Theory

Hadikhani¹,

Lai²,

Ong³

2022

Preprint

View full text Add to dashboard Cite

Despite many advances in human activity recognition, most existing works are conducted with supervision. Supervised methods rely on labeled training data. However, obtaining labeled data is difficult, costly, and time-consuming. In this paper, we introduce an automatic multi-objective particle swarm optimization clustering based on Gaussian mutation and game theory (MOPGMGT) to tackle the problem of human activity discovery fully unsupervised and map the multi-objective clustering problem to game theory to get the best optimal solution. The proposed algorithm does not require any prior knowledge of the number of activities to be discovered and can find the optimal number. Multi-objective optimization problems typically cannot have a single optimal solution. To solve this issue, Nash Equilibrium (NE) is applied to the pareto front to choose the best solution. NE does not just look for the best solution, but tries to optimize the final solution by considering the effect of choosing each of the solutions as the best solution on the other solutions and one with the best impact is chosen. Moreover, a Gaussian mutation is applied on the pareto front to avoid premature convergence. Experiments on five challenging datasets demonstrate that the proposed approach is the most efficient to achieve better accuracy in human activity discovery and also can determine the optimal number of clusters.

show abstract

“…The recent success in skeleton-based HAR, particularly by adopting deep learning methodologies, primarily relies on the supervised learning paradigm [3,31,34]. However, data annotation is expensive, time-consuming, and prone to human errors [20]. As a (recent) alternative, unsupervised approaches [7,9,12,18,22,28,30,35] are continuously reducing the performance gap with the fully supervised counterpart while dismissing the strong reliance over annotated data.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance

Paoletti¹,

Cavazza²,

Beyan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a novel end-to-end method for the problem of skeleton-based unsupervised human action recognition. We propose a new architecture with a convolutional autoencoder that uses graph Laplacian regularization to model the skeletal geometry across the temporal dynamics of actions. Our approach is robust towards viewpoint variations by including a self-supervised gradient reverse layer that ensures generalization across camera views. The proposed method is validated on NTU-60 and NTU-120 large-scale datasets in which it outperforms all prior unsupervised skeleton-based approaches on the cross-subject, cross-view, and cross-setup protocols. Although unsupervised, our learnable representation allows our method even to surpass a few supervised skeleton-based action recognition methods. The code is available in: www.github. com/IIT-PAVIS/UHAR_Skeletal_Laplacian

show abstract

Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning

Cited by 31 publications

References 40 publications

Flexible Multi-Objective Particle Swarm Optimization Clustering with Game Theory to Address Human Activity Recognition Fully Unsupervised

Flexible Multi-Objective Particle Swarm Optimization Clustering with Game Theory to Address Human Activity Recognition Fully Unsupervised

Human Activity Discovery with Automatic Multi-objective Particle Swarm Optimization Clustering with Gaussian Mutation and Game Theory

Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance

Contact Info

Product

Resources

About