Automatic live tagging of videos using chronicles
Abstract:
Creating and editing videos is a costly process in terms of time and money. For this reason, reusability is a major issue in this field; hence, videos should be appropriately labelled, describing its structure and content, but this process is costly too. However, for some types of videos, this information is already expressed as structured text. In this paper, we present an automatic tagging system to describe the structure and semantics of the videos for sports events, extracting information from the chronicles for these events written in the web pages of some journals or sports organisations.
Año de publicación:
2008
Keywords:
- Natural Language processing
- information extraction
- Automatic tagging
- Metadata
Fuente:
scopus
Tipo de documento:
Conference Object
Estado:
Acceso restringido
Áreas de conocimiento:
- Aprendizaje automático
- Simulación por computadora
Áreas temáticas:
- Métodos informáticos especiales
- Experiencia, vida y práctica religiosas
- Física aplicada