Region-Based Artificial Visual Attention in Space and Time

Tünnermann, Jan; Mertsching, Bärbel

doi:10.1007/s12559-013-9220-5

Cited by 17 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [16], [17] works state the use of application in personal assistance field. The authors of [18], [19] refers application in the ubiquitous environmental information domain. With increasing attention towards the development of approaches to deal drift concept, there has been an ample literature enhancement.…”

Section: Review Of the Literaturementioning

confidence: 99%

“…The tabular representation of the contemporary models reviewed in this section follows (see Table 1). [10], [11] Field-of-medicine; [12], [13] Monitoring-and-control sector; [14], [15] Management-and-strategic-planning domain; [16], [17] Personal-assistance-field; [18], [19] Ubiquitous-environmental-information-domain. [2], [7], [22] Surveys [27] Network-intrusion-detection field Unsupervised [23] Univariate Outlier-detection [24], [25], [26] Multivariate By example models, can't react to the changes occurred in the correlated components considered [27], [28] Multivariate solo monitoring of components using ensemble scalar CDT, every single component of the data stream is inspected to detect concept drift in a multivariate data, can't react to the changes occurred in the correlated components considered [29], [30] Multivariate nonparametric density models [31], [32], [26] Multivariate 'Pure' detectors, outperform with a low volume of data Supervised [33] Machine learning Uses commonly selected sequences as Hidden Markov Models, limits to define simple patterns.…”

Section: Review Of the Literaturementioning

confidence: 99%

See 1 more Smart Citation

Data Mining Models of High Dimensional Data Streams, and Contemporary Concept Drift Detection Methods: a Comprehensive Review

Kumar¹,

Kumar²,

Prasanna³

2018

IJET

View full text Add to dashboard Cite

Concept drift is defined as the distributed data across multiple data streams that change over the time. Concept drift is visible only when the type of collected data changes after some stable period. The emergence of concept drift in data streams leads to increase misclassification and performing degradation of data streams. In order to obtain accurate results, identification of such concept drifts must be visible. This paper focused on a review of the issues related to identifying the changes occurred in the various multivariate high dimensional data streams. The insight of the manuscript is probing the inbuilt difficulties of existing contemporary change-detection methods when they encounter during data dimensions scales.

show abstract

Section: Review Of the Literaturementioning

confidence: 99%

Section: Review Of the Literaturementioning

confidence: 99%

Data Mining Models of High Dimensional Data Streams, and Contemporary Concept Drift Detection Methods: a Comprehensive Review

Kumar¹,

Kumar²,

Prasanna³

2018

IJET

View full text Add to dashboard Cite

show abstract

“…Cheng et al [27] segmented the input image into subregions, then, computed color contrast at the region level, and defined the saliency for each region as the weighted sum of the regions contrasts to all other regions in the image. Tünnermann and Mertsching [30] extended this concept to the spatiotemporal domain to create a full-featured integration of spatial and temporal systems. Although most of region-based methods are not subject to the edge bias, these approaches yield the poor performance in highly textured areas because they are frequently oversegmented into several fragments (see Fig.…”

Section: Review Of Bottom-up Saliencymentioning

confidence: 99%

Spatiotemporal Saliency Detection Using Textural Contrast and Its Applications

Kim

2014

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Saliency detection has been extensively studied due to its promising contributions for various computer vision applications. However, most existing methods are easily biased toward edges or corners, which are statistically significant, but not necessarily relevant. Moreover, they often fail to find salient regions in complex scenes due to ambiguities between salient regions and highly textured backgrounds. In this paper, we present a novel unified framework for spatiotemporal saliency detection based on textural contrast. Our method is simple and robust, yet biologically plausible; thus, it can be easily extended to various applications, such as image retargeting, object segmentation, and video surveillance. Based on various datasets, we conduct comparative evaluations of 12 representative saliency detection models presented in the literature, and the results show that the proposed scheme outperforms other previously developed methods in detecting salient regions of the static and dynamic scenes.Index Terms-Comparative evaluations, computer vision applications, human visual attention, saliency detection, textural contrast.

show abstract

“…They detected saliency maps by performing temporal spectral residual analysis on video slices along X-T and Y -T planes. Tünnermann and Mertsching [29] proposed a region-based approach to saliency detection. They extended the region-based attention to the spatiotemporal domain to compile motion saliency, and then presented a biologically inspired system that integrated both spatial and motion saliency to grab static and dynamic stimuli.…”

Section: B Motion-aware Visual Attentionmentioning

confidence: 99%

Video Saliency Map Detection by Dominant Camera Motion Removal

Huang

Chang

Zhi

et al. 2014

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

We present a trajectory-based approach to detect salient regions in videos by dominant camera motion removal. Our approach is designed in a general way so that it can be applied to videos taken by either stationary or moving cameras without any prior information. Moreover, multiple salient regions of different temporal lengths can also be detected. To this end, we extract a set of spatially and temporally coherent trajectories of keypoints in a video. Then, velocity and acceleration entropies are proposed to represent the trajectories. In this way, long-term object motions are exploited to filter out short-term noises, and object motions of various temporal lengths can be represented in the same way. On the other hand, we are inspired by the observation that the trajectories in backgrounds, i.e., the nonsalient trajectories, are usually consistent with the dominant camera motion no matter whether the camera is stationary or not. We make use of this property to develop a unified approach to saliency generation for both stationary and moving cameras. Specifically, one-class SVM is employed to remove the consistent trajectories in motion. It follows that the salient regions could be highlighted by applying a diffusion process to the remaining trajectories. In addition, we create a set of manually annotated ground truth on the collected videos. The annotated videos are then used for performance evaluation and comparison. The promising results on various types of videos demonstrate the effectiveness and great applicability of our approach.Index Terms-One-class SVM (OCSVM), trajectory, video saliency map. 1051-8215

show abstract

Region-Based Artificial Visual Attention in Space and Time

Cited by 17 publications

References 30 publications

Data Mining Models of High Dimensional Data Streams, and Contemporary Concept Drift Detection Methods: a Comprehensive Review

Data Mining Models of High Dimensional Data Streams, and Contemporary Concept Drift Detection Methods: a Comprehensive Review

Spatiotemporal Saliency Detection Using Textural Contrast and Its Applications

Video Saliency Map Detection by Dominant Camera Motion Removal

Contact Info

Product

Resources

About