Temporal Relations in Videos for Unsupervised Activity Analysis

Nater, Fabian; Gräbner, Helmut; Gool, Luc J. Van

doi:10.5244/c.25.21

Cited by 15 publications

(22 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the works by Nater et al [12,13], simple tracker hierarchies are arranged in a tree-structure to analyze human behavior. However, they only consider temporal interdependencies and hence can not separate two atomic activities happening at the same time.…”

Section: Previous Workmentioning

confidence: 99%

A combination of generative and discriminative models for fast unsupervised activity recognition from traffic scene videos

Krishna

Denzler

2014

IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

Recent approaches in traffic and crowd scene analysis make extensive use of non-parametric hierarchical Bayesian models for intelligent clustering of features into activities. Although this has yielded impressive results, it requires the use of time consuming Bayesian inference during both training and classification. Therefore, we seek to limit Bayesian inference to the training stage, where unsupervised clustering is performed to extract semantically meaningful activities from the scene. In the testing stage, we use discriminative classifiers, taking advantage of their relative simplicity and fast inference. Experiments on publicly available data-sets show that our approach is comparable in classification accuracy to state-of-the-art methods and provides a significant speed-up in the testing phase.

show abstract

Section: Previous Workmentioning

confidence: 99%

A combination of generative and discriminative models for fast unsupervised activity recognition from traffic scene videos

Krishna

Denzler

2014

IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

show abstract

“…Generally,ẏ j is represented as the difference between consecutive time steps,ẏ j (x t ) = y j (x t ) − y j (x t−1 ) [5,4,2].…”

Section: Slow Feature Analysismentioning

confidence: 99%

“…In [2], its properties are exploited to segment videos temporally. The individual segments are thought to be the activities in the video.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incremental Slow Feature Analysis with Indefinite Kernel for Online Temporal Video Segmentation

Liwicki

Zafeiriou

Pantić

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA's first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.

show abstract

“…However, until today limited research has been conducted regarding its efficacy on computer vision problems [8,13,14,15,26]. Recently, SFA and its discriminant extensions have been successfully applied for human action recognition in [26], while hierarchical segmentation of video sequences using SFA was investigated in [15].…”

Section: Introductionmentioning

confidence: 99%

Learning Slow Features for Behaviour Analysis

Zafeiriou

Nicolaou

Zafeiriou

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

A recently introduced latent feature learning technique for time varying dynamic phenomena analysis is the socalled Slow Feature Analysis (SFA). SFA is a deterministic component analysis technique for multi-dimensional sequences that by minimizing the variance of the first order time derivative approximation of the input signal finds uncorrelated projections that extract slowly-varying features ordered by their temporal consistency and constancy. In this paper, we propose a number of extensions in both the deterministic and the probabilistic SFA optimization frameworks. In particular, we derive a novel deterministic SFA algorithm that is able to identify linear projections that extract the common slowest varying features of two or more sequences. In addition, we propose an Expectation Maximization (EM) algorithm to perform inference in a probabilistic formulation of SFA and similarly extend it in order to handle two and more time varying data sequences. Moreover, we demonstrate that the probabilistic SFA (EM-SFA) algorithm that discovers the common slowest varying latent space of multiple sequences can be combined with dynamic time warping techniques for robust sequence timealignment. The proposed SFA algorithms were applied for facial behavior analysis demonstrating their usefulness and appropriateness for this task.

show abstract

Temporal Relations in Videos for Unsupervised Activity Analysis

Cited by 15 publications

References 21 publications

A combination of generative and discriminative models for fast unsupervised activity recognition from traffic scene videos

A combination of generative and discriminative models for fast unsupervised activity recognition from traffic scene videos

Incremental Slow Feature Analysis with Indefinite Kernel for Online Temporal Video Segmentation

Learning Slow Features for Behaviour Analysis

Contact Info

Product

Resources

About