Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
In this paper, we present a novel approach to recognizing human actions from different views by view knowledge transfer. An action is originally modelled as a bag of visual-words ...
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
Given sensors to detect object use, commonsense priors of object usage in activities can reduce the need for labeled data in learning activity models. It is often useful, however,...
Shiaokai Wang, William Pentney, Ana-Maria Popescu,...
This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures ...
Imran N. Junejo, Emilie Dexter, Ivan Laptev, Patri...