In this paper we present a statistical learning scheme for image classification based on a mixture of old fashioned ideas and state of the art learning tools. We represent input i...
We tested our image classification methodology in the photo-annotation task of the ImageCLEF competition [Nowak, 2010] using a visual-only approach performing automated labeling. ...
Query-by-example is the most popular query model for today’s image retrieval systems. A typical query image contains not only relevant objects (e.g., Eiffel Tower), but also ir...
Content-based image retrieval is a fairly new discipline. Yet research in this field has highlighted many approaches that show good performance in specific subproblems using singl...
Maria Grazia Albanesi, Marco Ferretti, Alessandro ...
We present metrics to evaluate the performance of video object segmentation and tracking methods quantitatively when groundtruth segmentation maps are not available. The proposed ...