In this paper, we propose an effective method for emergent leader detection in meeting environments which is based on nonverbal visual features. Identifying emergent leader is an important issue for organizations. It is also a wellinvestigated topic in social psychology while a relatively new problem in social signal processing (SSP). The effectiveness of nonverbal features have been shown by many previous SSP studies. In general, the nonverbal video-based features were not more effective compared to audio-based features although, their fusion generally improved the overall performance. However, in absence of audio sensors, the accurate detection of social interactions is still crucial. Motivating from that, we propose novel, automatically extracted, nonverbal features to identify the emergent leadership. The extracted nonverbal features were based on automatically estimated visual focus of attention which is based on head pose. The evaluation of the proposed method and the defined features were realized using a new dataset which is firstly introduced in this paper including its design, collection and annotation. The effectiveness of the features and the method were also compared with many state of the art features and methods.
Figure 1: Combining automatic and manual segmentation methods. Visualizing and browsing the topological structure of the resulting decomposition.
AbstractModels of 3D objects have become widely accessible in several disciplines within academia and industry, spanning from scientific visualization to entertainment. In the last few years, 3D models are often organized into digital libraries accessible over the network, and thus semantic annotation of such models becomes an important issue. A fundamental step in annotating a 3D model is to segment it into meaningful parts. In this work, we present a Java3D framework for inspecting and segmenting 3D objects represented in X3D format. In particular, we present a combination of segmentation and merging techniques for producing a feasible decomposition of the boundary of a 3D object. We represent such decomposition as a graph, that we call the segmentation graph which is the basis for semantic annotation. We describe also the interface we have developed to allow visualization and browsing of both the decomposition and the segmentation graph in order to understand the topological structure of the resulting decomposition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.