In this paper, the recognition of the visual focus of attention (VFOA) of meeting participants (as defined by their eye gaze direction) from their head pose is addressed. To this ...
This paper presents a content-based approach for understanding handball videos. Tracked players are characterized by their 2D trajectories in the court plane. The trajectories and...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
Under natural viewing conditions, human observers use shifts in gaze to allocate processing resources to subsets of the visual input. There are many computational models that try ...
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
Extracting meaningful 3D human motion information from video sequences is of interest for applications like intelligent humancomputer interfaces, biometrics, video browsing and ind...