Audio Recurrence Contribution to a Video-based TV Program Structuring Approach

Abduraman, Alina Elma; Berrani, Sid-Ahmed; Mérialdo, Bernard

doi:10.1109/ism.2011.15

Search citation statements

Order By: Relevance

Paper Sections

Select...

Prior Filtering Module1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2013

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The isolated occurrences are likely to be false alarms. For more details about this method the reader may refer to (Abduraman et al, 2011a).…”

Section: Prior Filtering Modulementioning

confidence: 99%

Audio/Visual Recurrences and Decision Trees for Unsupervised TV Program Structuring

Abduraman¹,

Berrani²,

Mérialdo³

2013

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

This paper addresses the problem of unsupervised TV program structuring. Program structuring allows direct and non linear access to the desired parts of a program. Our work addresses the structuring of programs like news, entertainment, shows, magazines... It is based on the detection of audio and visual recurrences. It proposes an effective classification and selection system, based on decision trees, that allows the detection of "separators" among these recurrences. Separators are short audio/visual sequences that delimit the different parts of a program. The decision trees are built based on attributes issued from techniques like applause detection, scenes segmentation, face/speaker detection and clustering. The approach has been evaluated on a 112 hours dataset corresponding to 169 episodes of TV programs.

show abstract

“…The isolated occurrences are likely to be false alarms. For more details about this method the reader may refer to (Abduraman et al, 2011a).…”

Section: Prior Filtering Modulementioning

confidence: 99%