Fitting statistical 2D and 3D shape models to images is necessary for a variety of tasks, such as video editing and face recognition. Much progress has been made on local fitting...
The classification of urban landscape in aerial LiDAR point clouds is useful in 3D modeling and object recognition applications in urban environments. In this paper, we introduce ...
Improving coding and spatial pooling for bag-of-words based feature design have gained a lot of attention in recent works addressing object recognition and scene classification. ...
Many vision tasks are posed as either graph partitioning (coloring) or graph matching (correspondence) problems. The former include segmentation and grouping, and the latter inclu...
Facial activities are the most natural and powerful means of human communication. Spontaneous facial activity is characterized by rigid head movements, non-rigid facial muscular m...