2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Boston, MA, USA
June 7, 2015 to June 12, 2015
Justin Johnson , Stanford University, USA
Ranjay Krishna , Stanford University, USA
Michael Stark , Max Planck Institute for Informatics, USA
Li-Jia Li , Yahoo Labs, USA
David A. Shamma , Yahoo Labs, USA
Michael S. Bernstein , Stanford University, USA
Li Fei-Fei , Stanford University, USA
This paper develops a novel framework for semantic image retrieval based on the notion of a scene graph. Our scene graphs represent objects (“man”, “boat”), attributes of objects (“boat is white”) and relationships between objects (“man standing on boat”). We use these scene graphs as queries to retrieve semantically related images. To this end, we design a conditional random field model that reasons about possible groundings of scene graphs to test images. The likelihoods of these groundings are used as ranking scores for retrieval. We introduce a novel dataset of 5,000 human-generated scene graphs grounded to images and use this dataset to evaluate our method for image retrieval. In particular, we evaluate retrieval using full scene graphs and small scene subgraphs, and show that our method outperforms retrieval methods that use only objects or low-level image features. In addition, we show that our full model can be used to improve object localization compared to baseline methods.
J. Johnson et al., "Image retrieval using scene graphs," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 3668-3678.