Abstract. In this work, we propose a model-based approach for estimating the 3D position and orientation of a dummy's head for crash test video analysis. Instead of relying on...
Juergen Gall, Bodo Rosenhahn, Stefan Gehrig, Hans-...
Background modeling and subtraction to detect new or moving objects in a scene is an important component of many intelligent video applications. Compared to a single camera, the u...
Ser-Nam Lim, Anurag Mittal, Larry S. Davis, Nikos ...
The recognition of transitive, goal-directed actions requires a sensible balance between the representation of specific shape details of effector and goal object and robustness w...
Abstract. The estimation of camera motion is one of the most important aspects for video processing, analysis, indexing, and retrieval. Most of existing techniques to estimate came...
Jurandy Almeida, Rodrigo Minetto, Tiago A. Almeida...
The bag-of-words representation has attracted a lot of attention recently in the field of object recognition. Based on the bag-of-words representation, topic models such as Probab...