CONF quelhas:iccv:2005/IDIAP Modeling Scenes with Local Descriptors and Latent Aspects Quelhas, Pedro Monay, Florent Odobez, Jean-Marc Gatica-Perez, Daniel Tuytelaars, Tinne Gool, Luc Van EXTERNAL http://publications.idiap.ch/attachments/papers/2005/quelhas-iccv-2005.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/quelhas:rr04-79 Related documents IEEE Int. Conf. on Computer Vision 2005 IDIAP-RR 04-79 We present a new approach to model visual scenes in image collections, based on 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 latent space formulation can discover visual co-occurrence patterns, 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. REPORT quelhas:rr04-79/IDIAP Modeling Scenes with Local Descriptors and Latent Aspects Quelhas, Pedro Monay, Florent Odobez, Jean-Marc Gatica-Perez, Daniel Tuytelaars, Tinne Gool, Luc Van EXTERNAL http://publications.idiap.ch/attachments/reports/2004/quelhas-idiap-rr-04-79.pdf PUBLIC Idiap-RR-79-2004 2004 IDIAP Published in Proc. of IEEE int. Conf. on Computer Vision We present a new approach to model visual scenes in image collections, based on 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 latent space formulation can discover visual co-occurrence patterns, 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.