Maximally Stable Extremal Regions (MSERs) are one of the most prominent interest region detectors in computer vision due to their powerful properties and low computational demands...
Michael Donoser, Hayko Riemenschneider, Horst Bisc...
In this paper, we propose a method of text retrieval from document images using a similarity measure based on an N-Gram algorithm. We directly extract image features instead of us...
The bag-of-words (BoW) model treats images as an unordered set of local regions and represents them by visual word histograms. Implicitly, regions are assumed to be identically an...
Ramazan Gokberk Cinbis, Jakob J. Verbeek, Cordelia...
In this paper, we describe an investigation into the use of community annotations of photos for creating zoom and pan animations that present a time linear view of the regions of ...
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...