Learn More
We propose an appearance-based head pose estimation method that can be automatically adapted to individual scenes. Appearance-based estimation methods usually require a ground-truth dataset taken from a scene which is similar to test video sequences. However, it is almost impossible to acquire many manually-labeled head images for each scene. To address the(More)
Figure 1: The framework of our proposed approach. Given annotated dataset of pedestrian states, set of measurements based on attention-based and position-based cues is created for each pair of pedestrians. Estima-tor is then applied to construct set of decision trees representing group behavior models for social group discovery task. Abstract This paper(More)
  • 1