2013 · 131 citations · 27 references
ComputingComputer ScienceComputer VisionData MiningMachine LearningGraph-based LearningMetric LearningRepresentation LearningVisual LocalizationGraph Representation LearningLocation DatabasesLocation RepresentationPlace RecognitionVisual Connectivity Analysis
Recognizing the location of a query image by matching it to a database is an important problem in computer vision, and one for which the representation of the database is a key issue. 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 a bag-of-words-based location recognition method. In particular, starting from a graph on a set of images based on visual connectivity, we propose a method for selecting a set of sub graphs and learning a local distance function for each using discriminative techniques. For a query image, each database image is ranked according to these local distance functions in order to place the image in the right part of the graph. In addition, we propose a probabilistic method for increasing the diversity of these ranked database images, again based on the structure of the image graph. We demonstrate that our methods improve performance over standard bag-of-words methods on several existing location recognition datasets.
27
LIBLINEAR: A Library for Large Linear Classification
Rong-En Fan, Kai‐Wei Chang, Cho‐Jui Hsieh et al. · 2008 · 6.6K citations
Video Google: a text retrieval approach to object matching in videos
Object retrieval with large vocabularies and fast spatial matching
James Philbin, Ondřej Chum, Michael Isard et al. · 2007 · 3K citations
Three things everyone should know to improve object retrieval
Relja Arandjelović, Andrew Zisserman · 2012 · 1.4K citations