Explicit surfaces, such as triangulations or wireframe models, have been extensively used to represent the deformable 3?D models that are used to fit 3?D point and 2?D silhouette ...
We propose the use of 3D (2D+time) Shape Context to recognize the spatial and temporal details inherent in human actions. We represent an action in a video sequence by a 3D point ...
Franziska Meier, Irfan A. Essa, Matthias Grundmann
Current methods for finding relevant content, especially in media-rich web environments, suggest that metadata is critical for accurate and efficient information retrieval. We des...
In this paper I show a variety of ways to represent and think about statistical aspects of CHI and its sister conferences. In particular, I look at author counts, gender analysis,...
— In this paper, we present a novel relevance feedback method for Content-Based Image Retrieval systems based on dynamic feature weights. The proposed method utilizes intracluste...