This paper describes our participation to the TRECVID 2009 challenge [5]. This year, we focused on an optimized fusion by means of Genetic Algorithm. We have implemented a classical approach for concept detection in video shots based on low-level and intermediate features extraction, supervised classifiers and fusion process. We compare the genetic fusion with usual late fusion (sum or weighted...

We describe the MusicMiner system for organizing large collections of music with databionic mining techniques. Low level audio features are extracted from the raw audio data on short time windows during which the sound is assumed to be stationary. Static and temporal statistics were consistently and systematically used for aggregation of low level features to form high level features. A supervi...

Extracting features from an image is the first step in many computer vision applications. Traditionally, features represent physical or visual primitives such as edges and corners. In this paper, we augment the definition to include any attributes that conveniently describe the correlation and contextual relation between the primitive and its neighbors. The augmentation allows us to design a mo...

We describe a system which is designed to assist animators in extracting high-level information from sequences of images. The system is not meant to replace animators, but to be a tool to assist them in creating the first ‘roughcut’ of a sequence quickly and easily. Using the system, short animations have been created in a very short space of time. We show that the method of principal component...

A novel approach for estimating articulated body posture and motion from monocular video sequences is proposed. Human pose is defined as the instantaneous two dimensional configuration (i.e.,the projection onto the image plane) of a single articulated body in terms of the position of a predetermined set of joints. First, statistical segmentation of the human bodies from the background is perfor...

This paper presents a novel framework for object detection in videos that considers both structural and temporal information. Detection is performed by first applying low-level feature extraction techniques in each frame of the video. Then, additional robustness is obtained by considering the temporal stability of videos, using particle filters and probability maps, which encode information abo...

Mid-level image features have been shown to be helpful to bridge the semantic gap between low-level and high-level image representations. Many existing methods to learn mid-level visual elements consider each mid-level feature individually, and do not take their mutual relationships into account. We follow the intuitive idea that learning discriminative combinations of visual elements can help ...

Recent work in unsupervised feature learning has focused on the goal of discovering high-level features from unlabeled images. Much progress has been made in this direction, but in most cases it is still standard to use a large amount of labeled data in order to construct detectors sensitive to object classes or other complex patterns in the data. In this paper, we aim to test the hypothesis th...