| Autor: |
Sid-Ahmed Berrani, Jean-Bernard Rault, Alina Elma Abduraman, Olivier Le Blouch |
| Rok vydání: |
2011 |
| Předmět: |
|
| Zdroj: |
Proceedings of the 2011 ACM international workshop on Automated media analysis and production for novel TV services. |
| DOI: |
10.1145/2072552.2072556 |
| Popis: |
This paper addresses the problem of unsupervised detection of recurrent audio segments in TV programs toward program structuring. Recurrent segments are the key elements in the process of program structuring. This allows a direct and non linear access to the main parts inside a program. It hence facilitates browsing within a recorded TV program or a program that is available on a TV-on-Demand service. Our work focuses on programs like entertainments, shows, magazines, news... It proposes an audio recurrence detection method. This is either applied over an episode or a set of episodes of the same program. Different types of audio descriptors are proposed and evaluated over an 65-hours video dataset corresponding to 112 episodes of TV programs. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
