This paper presents a motion attention model that aims at analyzing gesture saliency using context-related information at three different levels. At the first level, motion feature...
Matei Mancas, Donald Glowinski, Gualtiero Volpe, P...
Extremely crowded scenes present unique challenges to
video analysis that cannot be addressed with conventional
approaches. We present a novel statistical framework for
modeling...
Louis Kratz (Drexel University), Ko Nishino (Drexe...
Video retargeting is the process of transforming an existing video to fit the dimensions of an arbitrary display. A compelling retargeting aims at preserving the viewers’ exper...
In this paper, we develop a neurobiologicallymotivated statistical method for video analysis that simultaneously searches the combined motion and form space in a concerted and ef...
Computer vision systems for human-computer interaction have tended towards more precise forms of interface that require complex vision tasks such as segmentation, tracking, object...