Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an ...
McGuffin and Balakrishnan (M&B) have recently reported evidence that target expansion during a reaching movement reduces pointing time even if the expansion occurs as late as ...
Abstract—The development of human-robot interaction scenarios is a strongly situation-dependent as well as an extremely dynamic task. Humans interacting with the robot directly r...
Persons may perform an activity in many different styles, or noise may cause an identical activity to have different temporal structures. We present a robust methodology for recog...
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...