2012
DOI: 10.1007/s11432-012-4720-6
|View full text |Cite
|
Sign up to set email alerts
|

A temporal context model for boosting video annotation

Abstract: In this paper, we propose a new method to model the temporal context for boosting video annotation accuracy. The motivation of our idea mainly comes from the fact that temporally continuous shots in video are generally with relevant content, so that the performance of video annotation could be comparably boosted by mining the temporal dependency between shots in video. Based on this consideration, we propose a temporal context model to mine the redundant information between shots. By connecting our model with … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2015
2015
2016
2016

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 18 publications
0
2
0
Order By: Relevance
“…Then some filtration methods based on statistical information were performed. Because it is difficult for these methods to choose the appropriate threshold, some researchers try to combine machine learning strategies, such as support vector machine (SVM) [15][16][17][18], conditional random fields (CRF) [19,20], hidden Markov model (HMM) [21][22][23] and so on. Peng et al [8] and Xu et al [24] used the model of CRF.…”
Section: Related Workmentioning
confidence: 99%
“…Then some filtration methods based on statistical information were performed. Because it is difficult for these methods to choose the appropriate threshold, some researchers try to combine machine learning strategies, such as support vector machine (SVM) [15][16][17][18], conditional random fields (CRF) [19,20], hidden Markov model (HMM) [21][22][23] and so on. Peng et al [8] and Xu et al [24] used the model of CRF.…”
Section: Related Workmentioning
confidence: 99%
“…In previous works, the low-level or mid-level visual information in surrounding local regions was concatenated as context information [11,[15][16][17] or extracted mutual information by clustering [18]. However, structural information as context pattern information has not been well exploited.…”
Section: Introductionmentioning
confidence: 99%