In recent research, we have proposed a high-accuracy bottom-up detection-based paradigm for continuous phone speech recognition. The key component of our system was a bank of arti...
In this paper, we address invariant keypoint-based texture characterization and recognition. Viewing keypoint sets associated with visual textures as realizations of point process...
Spatiotemporal segmentation is an essential task for video analysis. The strong interconnection between finding an object's spatial support and finding its motion characterist...
Alex Levinshtein, Cristian Sminchisescu, Sven J. D...
This paper presents the Voronoi-clip, or V-clip, collision detection algorithm for polyhedral objects specified by a boundary representation. V-clip tracks the closest pair of fe...
In this paper, we propose a method of text retrieval from document images using a similarity measure based on an N-Gram algorithm. We directly extract image features instead of us...