Attribute-Graph: A Graph based approach to Image Ranking
This addresses image ranking for complex queries with multiple objects, but it appears incremental as it builds on graph-based methods.
The authors tackled image ranking by semantic similarity using a novel Attribute-Graph representation, which improved performance over existing techniques on the rPascal and rImageNet datasets.
We propose a novel image representation, termed Attribute-Graph, to rank images by their semantic similarity to a given query image. An Attribute-Graph is an undirected fully connected graph, incorporating both local and global image characteristics. The graph nodes characterise objects as well as the overall scene context using mid-level semantic attributes, while the edges capture the object topology. We demonstrate the effectiveness of Attribute-Graphs by applying them to the problem of image ranking. We benchmark the performance of our algorithm on the 'rPascal' and 'rImageNet' datasets, which we have created in order to evaluate the ranking performance on complex queries containing multiple objects. Our experimental evaluation shows that modelling images as Attribute-Graphs results in improved ranking performance over existing techniques.