The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
: Ubiquitous computing could help the organisation and the mediation of social interactions wherever and whenever these situations might occur. Using those technologies enables the...
Hiroaki Ogata, Chengjiu Yin, Moushir M. El-Bishout...
Recently, boosting is used widely in object detection applications because of its impressive performance in both speed and accuracy. However, learning weak classifiers which is on...
Abstract. This paper proposes a decision support system for tactical air combat environment using a combination of unsupervised learning for clustering the data and an ensemble of ...
Detection of visually salient image regions is useful for
applications like object segmentation, adaptive compression,
and object recognition. In this paper, we introduce
a meth...
Radhakrishna Achanta, Sheila S. Hemami, Francisco ...