PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Modeling Scenes with Local Descriptors and Latent Aspects
Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Daniel Gatica-Perez, Tinne Tuytelaars and Luc Van Gool
In: IEEE Int. Conf. on Computer Vision (ICCV), Oct. 2005, Beijing, China.


We present a new approach to model visual scenes in image collections, based on the use of local invariant features and probabilistic latent space models. Our formulation provides answers to three open questions:(1) whether the invariant local features are suitable for scene (rather than object) classification; (2) whether unsupervised latent space models can be used for feature extraction in the classification task; and (3) whether the probabilistic latent space formulation can discover patterns of visual co-occurrence, motivating novel approaches for image organization and segmentation. Using a 9500-image dataset, our approach is validated on each of these issues. First, we show with extensive experiments on binary and multi-class scene classification tasks, that a bag-of-visterm representation, derived from local invariant descriptors, consistently outperforms state-of-the-art approaches. Second, we show that Probabilistic Latent Semantic Analysis (PLSA) generates a compact scene representation, discriminative for accurate classification, and significantly more robust when less training data are available. Third, we have exploited the ability of PLSA to automatically extract visually meaningful aspects, to propose new algorithms for aspect-based image ranking and context-sensitive image segmentation.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
Learning/Statistics & Optimisation
ID Code:1276
Deposited By:Jean-Marc Odobez
Deposited On:28 November 2005