This paper presents an integrated approach for robustly locating facial landmark for drivers. In the first step a cascade of probability learners is used to detect the face edge primitives from fine to coarse, so that faces with variant head poses can be located. The edge density descriptors and skin-tone color features are combined together as the basic features to examine the probability of a...

In this paper we describe our experiments in the automatic search task of TRECVid 2007. For this we have implemented a new video search technique based on SIFT features and manual annotation. We submitted two runs, one solely based on the SIFT features with keyframe matching and the other based on adapted SIFT features for video retrieval in addition to manually annotated data.

In this paper we describe an approach to recognizing poorly textured objects, that may contain holes and tubular parts, in cluttered scenes under arbitrary viewing conditions. To this end we develop a number of novel components. First, we introduce a new edge-based local feature detector that is invariant to similarity transformations. The features are localized on edges and a neighbourhood is ...

This paper proposes a high-precision, high-speed keypoint matching method using a two-stage Randomized Trees. The keypoint classification method uses the conventional Randomized Trees to enable highprecision, real-time keypoint matching. But the wide variety of view transformations for templates expressed by Randomized Trees make high-precision keypoint classification for all transformations di...

This paper describes the LIG participation to the MediaEval 2011 Affect Task on violent scenes’ detection in Hollywood movies. We submitted only the required run (shot classification run) with a minimal system using only the visual information. Color, texture and SIFT descriptors were extracted from key frames. The performance of our system was below the performance of the systems using both au...

The growth of computational capabilities together with the emergence of vision techniques have opened new opportunities for the development of new approaches for video-surveillance systems (people detection, tracking and recognition...). The current work addresses the issue of visual real-time people tracking within a multi-camera network. We studied three different techniques for visual signat...

1. Briefly, what approach or combination of approaches did you test in each of your submitted runs?  KB_lab: This system extracts the facial image from each cut scene frame using the Haar-like operator, and then eliminates noise images (non-facial image) using SVM. Next, SIFT features are detected from the true facial image, and the similarity of the facial image is calculated using the SIFT f...

Recent years have seen a lot of work on local descriptors. In all published comparisons or evaluations, the now quite well-known SIFT-descriptor has been one of the top performers. For the application of object pose estimation, one comparison showed a local descriptor, called the Patch-Duplet, of equal or better performance than SIFT. This paper examines different properties of those two descri...

In this paper, we described the latest video semantic indexing systems developed at France Telecom Orange Labs (Beijing). In our previous systems for TRECVID 2009, the features of color, edge, texture and SIFT were used. This year, some new features based on local descriptors were added for performance improvement. Three Full runs (130 concepts) based on later fusion and one Light run (10 conce...