We develop and evaluate a novel data compression strategy for visual SLAM centered on traveled trajectory analysis. Beyond compressing scene structure based purely on geometrical information as commonly done, we aim at developing representations that are useful for re-exploration, that use low memory footprint and low CPU computation. Our work is evaluated on data collected from a visual sensor...

This paper presents an integrated framework for interactive content-based retrieval in video databases by means of visual queries. The proposed system incorporates algorithms for video shot detection, keyframe and shot selection, automated video object segmentation and tracking, and construction of multidimensional feature vectors using fuzzy classification of color, motion or texture segment p...

Previous work in the animation of plant development and expansion has centered on the botom-up approach, whereby models are specified in terms of developmental ruls. These models are inherently difficult to use for goal oriented modeling as the final structure and development of these models are emergent properties. Top-down modeling has previously been introduced to remedy this problem by allo...

We present methods for semantic annotation of multimedia data. The goal is to detect semantic attributes (also referred to as concepts) in clips of video via analysis of a single keyframe or set of frames. The proposed methods integrate high performance discriminative single concept detectors in a random field model for collective multiple concept detection. Furthermore, we describe a generic f...

We present a comprehensive evaluation of performance of shot-based visual feature representations for MediaEval 2012 Violent Scenes Detection Affect Task. In spite of using keyframe-based as last year, we try to apply shot-based features using the global features (color moments, color histogram, edge orientation histogram, and local binary patterns) for violent scenes detection. Besides that, w...

Recovering surgical scene structure in laparoscope surgery is crucial step for surgical guidance and augmented reality applications. In this paper, a quasi dense reconstruction algorithm of surgical scene is proposed. This is based on a state-of-the-art SLAM system, and is exploiting the initial exploration phase that is typically performed by the surgeon at the beginning of the surgery. We sho...

We build a fast video shot retrieval system in the context of the NIST TREC Video 2009 evaluation campaign. We compare our efficient Profile Entropy Features (PEF) to usual features, using various classifiers. These PEF are derived using the projection in the horizontal and vertical orientations. These features are then fed to SVM or KNNG classifiers to produce the keyframe ranks, from which we...

This paper addresses the problem of how to learn an appropriate representation from video to benefit video-based face recognition. We pose it as learning spatio-temporal embedding (STE) from raw video. STE of a video sequence is defined as its condensed version capturing the essence of space-time characteristics of the video. Relying on co-occurrence statistics of training videos, Bayesian keyf...

These techniques are important because they allow to visualize any geometrical, physical or chemical situation to be visualized at any given time. However, the most interesting aspect of many phenomena is their evolution over time; e.g. motion of electromechanical devices (robots), chemical reactions, fluid motion, cloud motions, heat conduction. Experiments are often very expensive and sometim...

Keyframing is a popular method for animating articulated figures because it allows artistic expressiveness by providing control to the animator. The animator defines a movement by providing a set of poses. The motion is then obtained by simply interpolating between these keyframes, typically with cubic splines. The drawback of this process is that it requires significant effort from the animato...