In this paper, we present a novel approach to robust skeleton extraction. We use undirected graphs to model connectivity of the skeleton points. The graph topology remains unchang...
Opportunistic activity and context recognition systems do not presume a static sensor infrastructure that is defined at the design time of a system. They also do not have a fixed ...
We present a new approach for recognition of complex graphic symbols in technical documents. Graphic symbol recognition is a well known challenge in the field of document image an...
Muhammad Muzzamil Luqman, Thierry Brouard, Jean-Yv...
This paper presents a novel approach to skim and describe 3D videos. 3D video is an imaging technology which consists in a stream of 3D models in motion captured by a synchronized ...
Tony Tung (Kyoto University), Takashi Matsuyama (K...
Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...