Appropriate datasets are required at all stages of object recognition research, including learning visual models of object and scene categories, detecting and localizing instances ...
Jean Ponce, Tamara L. Berg, Mark Everingham, David...
This paper describes an online learning based method to detect flames in video by processing the data generated by an ordinary camera monitoring a scene. Our fire detection method...
We present a new algorithm to detect humans in still images utilizing covariance matrices as object descriptors. Since these descriptors do not lie on a vector space, well known m...
We face the problem of novelty detection from stream data, that is, the identification of new or unknown situations in an ordered sequence of objects which arrive on-line, at cons...
Online learning has shown to be successful in tracking of previously unknown objects. However, most approaches are limited to a bounding-box representation with fixed aspect rati...