This paper proposes a data mining approach to modeling relationships among categories in image collection. In our approach, with image feature grouping, a visual dictionary is cre...
We present a compact representation for human action recognition in videos using line and optical flow histograms. We introduce a new shape descriptor based on the distribution of...
Nazli Ikizler, Pinar Duygulu, Ramazan Gokberk Cinb...
Abstract. Feature extraction based on evolutionary search offers new possibilities for improving classification accuracy and reducing measurement complexity in many data mining and...
This paper describes how a visual system can automatically define features of interest from the observation of a large enough number of natural images. The principle complements t...
Background blurring is an effective way to both preserving privacy and keeping communication effective during video conferencing. This paper proposes a light weight real-time algo...