A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.

/pdf/a-model-of-saliency-based-visual-attention-for-rapid-scene-wv0n3yqxix.pdf

A model of saliency-based visual attention for rapid scene analysis

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralbas "gist" and Lowes SIFT descriptors.

/pdf/beyond-bags-of-features-spatial-pyramid-matching-for-4aa5cbe2fz.pdf

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

Extraction of interesting regions with bottom-up visual attention

Des feedbacks biaises de controle et de valeur ont ete utilises pour influencer l’evaluation emotionnelle pendant un jeu collaboratif de resolution de probleme. Nous avons etudie comment ces feedbacks ont module l’intensite des emotions ressenties ainsi que les relations entre les emotions, la collaboration percue et la performance du groupe. Les resultats montrent des patterns de correlations entre emotions, processus socio-cognitifs et performance differents en fonction des perceptions de controle et de valeur.

/pdf/effet-des-antecedents-emotionnels-de-controle-et-de-valeur-1sjxyxw8hl.pdf

Effet des antécédents émotionnels de contrôle et de valeur sur la résolution de problème dans un jeu vidéo collaboratif

In this paper, we tackle the problem of performance improvement of quantization-based data-hiding in the middle-watermark-to-noise ratio (WNR) regime. The objective is to define the quantization-based framework that maximizes the performance of the known-host-state data-hiding in the middle-WNR taking into account the host probability density function (pdf). The experimental results show that the usage of uniform deadzone quantization (UDQ) permits to achieve higher performance than using uniform quantization (UQ) or spread spectrum (SS)-based data-hiding. The performance enhancement is demonstrated for both achievable rate and error probability criteria.

/pdf/performance-analysis-of-nonuniform-quantization-based-data-4i7qxe7yze.pdf

Performance analysis of nonuniform quantization-based data hiding

As computer vision research shifts from smaller applications to more general object recognition problems which involve very large sets of object classes, there is an increasing amount of interest in feature indexing schemes. Feature indexing raises the important issue of how to construct a knowledge base of associations between key discriminative features and their respective object classes. It is clear that some amount of automation is necessary in order to build such knowledge bases for very large recognition systems.

/pdf/extracting-a-domain-theory-from-natural-language-to-5760e1u2p2.pdf

Extracting a Domain Theory from Natural Language to Construct a Knowledge Base for Visual Recognition

Saillance, zone d'intérêt, mise en correspondance: trois techniques pour la localisation et la reconnaissance d'objets en couleur sur fond fortement texturé

Thierry Pun

Papers

Extraction of interesting regions with bottom-up visual attention

Effet des antécédents émotionnels de contrôle et de valeur sur la résolution de problème dans un jeu vidéo collaboratif

Performance analysis of nonuniform quantization-based data hiding

Extracting a Domain Theory from Natural Language to Construct a Knowledge Base for Visual Recognition

Saillance, zone d'intérêt, mise en correspondance: trois techniques pour la localisation et la reconnaissance d'objets en couleur sur fond fortement texturé