The paper makes three points of significance for IR research: (1) The Cranfield paradigm of IR evaluation seems to lose power when one looks at human instead of system performance....
Given a large repository of geotagged imagery, we seek to automatically find visual elements, e.g. windows, balconies, and street signs, that are most distinctive for a certain g...
Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef ...
We give a fresh look into score normalization for merging result-lists, isolating the problem from other components. We focus on three of the simplest, practical, and widelyused l...
Search engines crawl and index webpages depending upon their informative content. However, webpages — especially dynamically generated ones — contain items that cannot be clas...
We take a fresh look at the logics of informational dependence and independence of Hintikka and Sandu and V¨a¨an¨anen, and their compositional semantics due to Hodges. We show h...