Learn More
This paper presents an appearance-based method for estimating head direction that automatically adapts to individual scenes. Appearance-based estimation methods usually require a ground-truth dataset taken from a scene that is similar to test video sequences. However, it is almost impossible to acquire many manually labeled head images for each scene. We(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)
This paper presents an approach to discover social groups in surveillance videos by incorporating attention-based cues to model group behaviors of pedestrians in videos. Group behaviors are modeled as a set of decision trees with the decisions being basic measurements based on position-based and attention-based cues. Rather than enforcing explicit models,(More)
  • 1