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

https://vision.unige.ch/publications/postscript/2003/SP-SpecialSection2003_SecureHybridRobustWatermarking.pdf

Secure hybrid robust watermarking resistant against tampering and copy attack

Attention mechanisms extract regions of interest from image data to reduce the amount of information to be analyzed by time-consuming processes such as image transmission, robot navigation, and object recognition. Two such mechanisms are described. The first one is an alerting system that extracts moving objects in a sequence through the use of multiresolution representations. The second one detects regions in still images that are likely to contain objects of interest. Two types of cues are used and integrated to compute the measure of interest. First, bottom-up cues result from the decomposition of the input image into a number of feature and conspicuity maps. The second type of cues is top-down, and is obtained from a priori knowledge about target objects, represented through invariant models. Results are reported for both the alerting and the attention mechanisms using cluttered and noisy scenes.

/pdf/attentive-mechanisms-for-dynamic-and-static-scene-analysis-1a0qlv7jjg.pdf

Attentive mechanisms for dynamic and static scene analysis

This paper presents an efficient method for the estimation and recovering from nonlinear or local geometrical distortions, such as the random bending attack and restricted projective transforms. The distortions are modeled as a set of local affine transforms, the watermark being repeatedly allocated into small blocks in order to ensure its locality. The estimation of the affine transform parameters is formulated as a robust penalized maximum likelihood (ML) problem, which is suitable for the local level as well as for global distortions. Results with the Stirmark benchmark confirm the high robustness of the proposed method and show its state-of-the-art performance.

/pdf/multibit-digital-watermarking-robust-against-local-nonlinear-h6j64nylhz.pdf

Multibit digital watermarking robust against local nonlinear geometrical distortions

This paper presents a new approach for the secure and robust copyright protection of digital images. A system for generating digital watermarks and for trading watermarked images is described. The system is based on a new watermarking technique, which is robust against image transformation techniques such as compression, rotation, translation, scaling and cropping. It uses modulation of the magnitude components in Fourier space to embed a watermark and an accompanying template and, during watermark extraction, reads a template in the log polar transform of the frequency domain. The template is used for analyzing scaling and rotation suffered by the watermarked stego-image. The detection of the watermarks is also possible without any need for the original cover-image. In addition, the system applies asymmetric cryptographic protocols for different purposes, namely embedding/detecting the watermark and transferring watermarked data. The public key technique is applied for the construction of a one-way watermark embedding and the verification function to identify and prove the uniqueness of the watermark. Legal dispute resolution is supported for the multiple watermarking of a digital image without revealing the confidential keying information.

/pdf/secure-copyright-protection-techniques-for-digital-images-1scvx3i17y.pdf

Secure Copyright Protection Techniques for Digital Images

In this paper, we propose an approach for affective representation of movie scenes based on the emotions that are actually felt by spectators. Such a representation can be used for characterizing the emotional content of video clips for e.g. affective video indexing and retrieval, neuromarketing studies, etc. A dataset of 64 different scenes from eight movies was shown to eight participants. While watching these clips, their physiological responses were recorded. The participants were also asked to self-assess their felt emotional arousal and valence for each scene. In addition, content-based audio- and video-based features were extracted from the movie scenes in order to characterize each one. Degrees of arousal and valence were estimated by a linear combination of features from physiological signals, as well as by a linear combination of content-based features. We showed that a significant correlation exists between arousal/valence provided by the spectator's self-assessments, and affective grades obtained automatically from either physiological responses or from audio-video features. This demonstrates the ability of using multimedia features and physiological responses to predict the expected affect of the user in response to the emotional video content.

/pdf/affective-characterization-of-movie-scenes-based-on-1096zfq1ms.pdf

Thierry Pun

Papers

Secure hybrid robust watermarking resistant against tampering and copy attack

Attentive mechanisms for dynamic and static scene analysis

Multibit digital watermarking robust against local nonlinear geometrical distortions

Secure Copyright Protection Techniques for Digital Images

Affective Characterization of Movie Scenes Based on Multimedia Content Analysis and User's Physiological Emotional Responses