In this article, we describe a feature selection algorithm which can automatically find relevant features for multiple instance learning. Multiple instance learning is considered a...
This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
Augmented Reality (AR) enables users to visualize synthetic information overlaid on a real video stream. Such visualization is achieved by tools that vary depending on the underlyi...
This paper presents an algorithm that detects and tracks marine vessels in video taken by a non-stationary camera installed on an untethered buoy. 1 The video is characterized by ...
The aim of this paper is to address the problem of recognizing human group activities in surveillance videos. This task has great potentials in practice, however was rarely studie...