Abstract

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.\n\nUsing 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.

Keywords

Probabilistic latent semantic analysisArtificial intelligenceComputer scienceDiscriminative modelPattern recognition (psychology)Probabilistic logicSegmentationFeature extractionInvariant (physics)Representation (politics)Contextual image classificationFeature vectorBag-of-words model in computer visionMachine learningImage (mathematics)Visual WordImage retrievalMathematics

Affiliated Institutions

Related Publications

Recognizing indoor scenes

We propose a scheme for indoor place identification based on the recognition of global scene views. Scene views are encoded using a holistic representation that provides low-res...

2009 2009 IEEE Conference on Computer Visi... 1464 citations

Publication Info

Year
2005
Type
article
Pages
883-890 Vol. 1
Citations
345
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

345
OpenAlex

Cite This

Pedro Quelhas, Florent Monay, Jean‐Marc Odobez et al. (2005). Modeling scenes with local descriptors and latent aspects. , 883-890 Vol. 1. https://doi.org/10.1109/iccv.2005.152

Identifiers

DOI
10.1109/iccv.2005.152