We explore new ways for exploiting the structure of a database by representing it as a graph, and show how the rich information embedded in a graph can improve ...

We explore new ways for exploiting the structure of a database by representing it as a graph, and show how the rich information embedded in a graph can improve ...

To do so, we use the graph's structure to define sets of images that are similar, and sets that are different, and use discriminative learning techniques to ...

Nov 12, 2014 · We explore new ways for exploiting the structure of an image database by representing it as a graph, and show how the rich information embedded in such a graph ...

We explore new ways for exploiting the structure of a database by representing it as a graph, and show how the rich information embedded in a graph can improve ...

Nov 25, 2024 · We explore new ways for exploiting the structure of an image database by representing it as a graph, and show how the rich information embedded ...

We explore new ways for exploiting the structure of an image database by representing it as a graph, and show how the rich information embedded in such a graph ...

We propose a method for selecting a set of overlapping subgraphs and learning a local distance function for each subgraph using discriminative techniques.

In this paper, we propose a low-rank graph preserving discriminative dictionary learning (LRGPDDL) method for sparse representation-based image recognition.

The prevalent approach to image-based localization is matching interest points detected in the query image to a sparse 3D point cloud representing the known ...