2004
DOI: 10.1007/978-3-540-28649-3_47
|View full text |Cite
|
Sign up to set email alerts
|

A Statistical Measure for Evaluating Regions-of-Interest Based Attention Algorithms

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0

Year Published

2009
2009
2014
2014

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 9 publications
(8 citation statements)
references
References 8 publications
0
8
0
Order By: Relevance
“…The method discussed in [6] extends the technique of [21] by arguing that the said method has a limitation of defining two regions of interest with equal importance as one ROI has to be always preferred over another in order to set up the ground truth and its labeling order. The proposed hybrid approach claims to be able to handle situations of order uncertainties in ROIs.…”
Section: A Survey Of Existing Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…The method discussed in [6] extends the technique of [21] by arguing that the said method has a limitation of defining two regions of interest with equal importance as one ROI has to be always preferred over another in order to set up the ground truth and its labeling order. The proposed hybrid approach claims to be able to handle situations of order uncertainties in ROIs.…”
Section: A Survey Of Existing Methodsmentioning
confidence: 99%
“…Since the sequence followed by one human observer cannot be preferred over another hence a feasible solution is to keep the sequence numbers of all human subjects in record. The evaluation method presented in [6] has also argued in favor of this concept. For this purpose the union operation in equation 5 considers two elements (Lp, Op) ∈ F Ho and (Lq, Oq) ∈ F Ho h as same when LpLq < r Λ and Op = Oq.…”
Section: Data Categorizationmentioning
confidence: 99%
“…The determination of ROI is closely related with attention and interest which are described in the literatures of [4], [5] and [6].This research implements the ROI selection in real time, therefore it is necessary to quote some relevant researches [7], [8]and [9] in this regard. The evaluation of ROI relevant with this research is reported in [10] and [11].…”
Section: Relevant Researchesmentioning
confidence: 99%
“…Salient Region detection and tracking in video is developed by Y. Li et al [9] .In [10] real time surveillance of people and their activities are presented. Martin Clauss et al [11] present an evaluation of ROI based on attention algorithm using probabilistic measure which handles situations of unordered ROIs. Paulo estimated video object's relevance using segmentation and evaluated with human observer in [12].…”
Section: Introductionmentioning
confidence: 99%
“…However, only selection of interesting objects has little meaning than the relation with other objects which are relevant to the most salient object. In [11], the Evaluation of ROI is demonstrated with simple test scenarios, not using real environment. In this paper, we have presented a clear formalization of the ROI detection and Evaluation problem.…”
Section: Introductionmentioning
confidence: 99%