Mining concept relationship in temporal context for effective video annotation

Yi, Jian; Peng, Yuxin; Xiao, Jianguo

doi:10.1145/2072298.2071936

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This part has nothing to do with lowlevel features and thus leads to a pure text-based processing: (2) As for the spatial-view term , we treat shots individually and only concern the concept correlations within shots. To take the content of into account, we incorporate its visual features into the estimation of spatial concept correlation and generate a data-specific correlation for .…”

Section: Two-view Concept Correlation Based Video Annotation Refimentioning

confidence: 99%

“…Therefore, recent studies begin to utilize this concept correlation to improve the annotation performance [1]- [7]. Among them, Content-Based Concept Fusion (CBCF) is one of the most popular approaches, in which concept correlation is integrated into a context-based model [2], [3] and acts as a post-processing to refine the initial results provided by multiple individual concept detectors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Two-View Concept Correlation Based Video Annotation Refinement

Zhong

Zhang

2012

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Recently, concept correlation defining the relationship between concepts has been playing an important role in video annotation (or concept detection). To improve the annotation performance, this paper presents a two-view concept correlation based video annotation refinement, using data-specific spatial and temporal concept correlations. Specifically, instead of generic concept correlation within shots, the spatial view estimates a data-specific concept correlation for each shot, via introducing concept correlation bases to map low-level features to high-level concept distribution under the framework of sparse representation. On the other hand, beyond the temporal consistency of one concept, a richer temporal correlation between different concepts respectively locating in the current shot and its neighbors is utilized to adjust the detection scores. In the end, these two types of concept correlations are integrated into a probability calculation based framework to refine the initial results derived from multiple concept detectors. And the experiments conducted on TRECVID 2006-2008 datasets and comparison with existing works demonstrate its effectiveness.

show abstract

Section: Two-view Concept Correlation Based Video Annotation Refimentioning

confidence: 99%