Automatically learning structural units in educational videos with the hierarchical hidden Markov models
Contribuinte(s) |
[Unknown] |
---|---|
Data(s) |
01/01/2004
|
Resumo |
In this paper we present a coherent approach using the hierarchical HMM with shared structures to extract the structural units that form the building blocks of an education/training video. Rather than using hand-crafted approaches to define the structural units, we use the data from nine training videos to learn the parameters of the HHMM, and thus naturally extract the hierarchy. We then study this hierarchy and examine the nature of the structure at different levels of abstraction. Since the observable is continuous, we also show how to extend the parameter learning in the HHMM to deal with continuous observations. |
Identificador | |
Idioma(s) |
eng |
Publicador |
IEEE |
Relação |
http://dro.deakin.edu.au/eserv/DU:30044633/venkatesh-automaticallylearning-2004.pdf http://dx.doi.org/10.1109/ICIP.2004.1421375 |
Direitos |
2004, IEEE |
Palavras-Chave | #Australia #content management #data mining #electronic learning #event detection #hidden Markov models #indexing #layout #motion pictures #videos |
Tipo |
Conference Paper |