Earth mover's prototypes: A convex learning approach for discovering activity patterns in dynamic scenes

Zen, Gloria; Ricci, Elisa

doi:10.1109/cvpr.2011.5995578

Cited by 33 publications

(68 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method has been tested on several video datasets, all of which are publicly available. The experimental results show that our approach successfully identifies high-level activities and spots anomalous patterns and it is very competitive with respect to state-of-the-art algorithms [2,3,5], often outperforming them.…”

Section: Introductionmentioning

confidence: 83%

“…However in this paper, to calculate motion features, we do not rely on noisy optical flow vectors but adopt a representation based on short trajectory snippets. Differently from previous works [1][2][3][4][5][6], we model the task of extracting salient activities as a matrix factorization problem and we consider as objective function the Earth Mover's Distance (EMD) [7], which is well-known to be a robust metric in case of noisy histogram comparison. To further reduce the influence of noisy data we also constrain the computed vector basis to be sparse.…”

Section: Introductionmentioning

confidence: 99%

“…These features are inevitably uncertain and noisy. Recent works [1][2][3][4][5][6] have shown how powerful statistical machine learning approaches can be used to implicitly handle noisy, uncertain visual information, leading to excellent results in terms of salient behaviors and anomalous activities identification. However none of the previous works have tackled explicitly this issue, i.e.…”

Section: Introductionmentioning

confidence: 99%

“…Many of them explicitly focused on analyzing complex and crowded scenes depicting public spaces in video surveillance applications [1][2][3][4][5][6]. Visual analysis of such complex scenes faces two main problems.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Exploiting Sparse Representations for Robust Analysis of Noisy Complex Video Scenes

Zen

Ricci

Sebe

2012

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Recent works have shown that, even with simple low level visual cues, complex behaviors can be extracted automatically from crowded scenes, e.g. those depicting public spaces recorded from video surveillance cameras. However, low level features as optical flow or foreground pixels are inherently noisy. In this paper we propose a novel unsupervised learning approach for the analysis of complex scenes which is specifically tailored to cope directly with features' noise and uncertainty. We formalize the task of extracting activity patterns as a matrix factorization problem, considering as reconstruction function the robust Earth Mover's Distance. A constraint of sparsity on the computed basis matrix is imposed, filtering out noise and leading to the identification of the most relevant elementary activities in a typical high level behavior. We further derive an alternate optimization approach to solve the proposed problem efficiently and we show that it is reduced to a sequence of linear programs. Finally, we propose to use short trajectory snippets to account for object motion information, in alternative to the noisy optical flow vectors used in previous works. Experimental results demonstrate that our method yields similar or superior performance to state-of-the arts approaches.

show abstract

Section: Introductionmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting Sparse Representations for Robust Analysis of Noisy Complex Video Scenes

Zen

Ricci

Sebe

2012

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Prior traffic anomaly detection (AD) approaches [3,31,35] typically adopt an unsupervised, one-class learning approach, where a model of normal behaviors is learned first, and used to subsequently detect abnormalities during the test phase. However, these methods do not effectively deal with the AD problem because of two main reasons: i) lack of effective video representations, and ii) the model of normal behaviors is learned offline and not updated as new data arrive.…”

Section: Introductionmentioning

confidence: 99%

Active Online Anomaly Detection Using Dirichlet Process Mixture Model and Gaussian Process Classification

Varadarajan

Subramanian

Ahuja

et al. 2017

2017 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We present a novel anomaly detection (AD) system for streaming videos. Different from prior methods that rely on unsupervised learning of clip representations, that are usually coarse in nature, and batch-mode learning, we propose the combination of two non-parametric models for our task: i) Dirichlet process mixture models (DPMM) based modeling of object motion and directions in each cell, and ii) Gaussian process based active learning paradigm involving labeling by a domain expert. Whereas conventional clip representation methods adopt quantizing only motion directions leading to a lossy, coarse representation that are inadequate, our clip representation approach results in fine grained clusters at each cell that model the scene activities (both direction and speed) more effectively. For active anomaly detection, we adapt a Gaussian Process framework to process incoming samples (video snippets) sequentially, seek labels for confusing or informative samples and and update the AD model online. Furthermore, the proposed video representation along with a novel query criterion to select informative samples for labeling that incorporates both exploration and exploitation criteria is proposed, and is found to outperform competing criteria on two challenging traffic scene datasets.

show abstract

Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations

Tur,

Dall’Asen,

Beyan

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Earth mover's prototypes: A convex learning approach for discovering activity patterns in dynamic scenes

Cited by 33 publications

References 10 publications

Exploiting Sparse Representations for Robust Analysis of Noisy Complex Video Scenes

Exploiting Sparse Representations for Robust Analysis of Noisy Complex Video Scenes

Active Online Anomaly Detection Using Dirichlet Process Mixture Model and Gaussian Process Classification

Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations

Contact Info

Product

Resources

About