No abstract

No abstract

Image memorability represents the degree to which images are remembered or forgotten after a period of time. Studying image memorability in computer vision is the task of finding special characteristics in memorable images, in order to develop a representative model of this type of images. Several approaches have been realised to examine features that can affect image memorability. In this study, the authors use bag‐of‐features as another kind of visual feature descriptor to assess image memorability. The authors’ method based on bag‐of‐visual‐words (BoVWs) technique involves four main steps. First, the authors extract local image features from regions/points of interest which are automatically detected. Then, they encode these local features by mapping them to a created visual vocabulary. Later, the authors apply features pooling and normalisation techniques to obtain image BoVW representation. Finally, the authors use this representation to examine image memorability as a problem of classification. They present different implementation choices for each step and compare reached results. The authors’ method performs best significant results in comparison with other approaches found in literature.

Generating execution plans is a costly operation for the DataBase Management System (DBMS). An interesting alternative to this operation is to reuse the old execution plans, that were already generated by the optimizer for past queries, to execute new queries. In this paper, we present an approach for execution plan recommendation in two phases. We firstly propose a textual representation of our SQL queries and use it to build a Features Extractor module. Then, we present a straightforward solution to identify query similarity.This solution relies only on the comparison of the SQL statements. Next, we show how to build an improved solution enabled by machine learning techniques. The improved version takes into account the features of the queries' execution plans. By comparing three machine learning algorithms, we find that the improved solution using Classification Based on Associative Rules (CAR) identifies similarity in 91% of the cases.

No abstract