This paper introduces a novel probabilistic activity modeling approach that mines recurrent sequential patterns from documents given as word-time occurrences. In this model, docum...
Active learning techniques have gained popularity in reducing human effort to annotate data instances for inducing a classifier. When faced with large quantities of unlabeled dat...
Human activity recognition and speech recognition appear to be two loosely related research areas. However, on a careful thought, there are several analogies between activity and ...
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
We present a novel approach for detecting global behaviour
anomalies in multiple disjoint cameras by learning
time delayed dependencies between activities cross camera
views. Sp...