In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A...
—Millions of surveillance cameras record video around the clock, producing huge video archives. Even when a video archive is known to include critical activities, finding them i...
Many activities may be characterized by a sequence of key frames that are related to important changes in motion rather than dominant characteristics that persist over a long seque...
Changes in motion properties of trajectories provide useful cues for modeling and recognizing human activities. We associate an event with significant changes that are localized in...
Naresh P. Cuntoor, B. Yegnanarayana, Rama Chellapp...
The recognition of transitive, goal-directed actions requires a sensible balance between the representation of specific shape details of effector and goal object and robustness w...