Characterisation and adaptive learning in interactive video retrieval
- Fernández Beltrán, Rubén
- Filiberto Pla Bañón Director
Defence university: Universitat Jaume I
Fecha de defensa: 20 May 2016
- Francesc Josep Ferri Rabasa Chair
- J. S. Sanchez Secretary
- Joan Isaac Biel Tres Committee member
Type: Thesis
Abstract
In this work, we are interested in the use of latent topics to overcome the current limitations in CBVR. Despite the potential of topic models to uncover the hidden structure of a collection, they have traditionally been unable to provide a competitive advantage in CBVR because of the high computational cost of their algorithms and the complexity of the latent space in the visual domain. Throughout this thesis we focus on designing new models and tools based on topic models to take advantage of the latent space in CBVR. Specifically, we have worked in four different areas within the retrieval process: vocabulary reduction, encoding, modelling and ranking, being our most important contributions related to both modelling and ranking.