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...
It has been established that active learning is effective for learning complex, subjective query concepts for image retrieval. However, active learning has been applied in a conc...
The ability to determine what day-to-day activity (such as cooking pasta, taking a pill, or watching a video) a person is performing is of interest in many application domains. A ...
Mike Perkowitz, Matthai Philipose, Kenneth P. Fish...
We propose a first attempt to classify events in static images by integrating scene and object categorizations. We define an event in a static image as a human activity taking pla...
We present a framework for the automatic recognition of complex multi-agent events in settings where structure is imposed by rules that agents must follow while performing activit...