Using Social-Network Metadata for Image Classification
- When?
- Tuesday 16 October 2012, 14:00 to 15:00
- Where?
- CVSSP Seminar Room (40bAB05)
- Open to:
- Public, Staff, Students
- Speaker:
- Dr Julian McAuley, University of Stanford
Many large-scale image retrieval benchmarks are derived from online photo sharing networks, like Flickr, which in addition to hosting images also provide a highly interactive social community. We study four such datasets, extending them with social-network metadata, which we harness for image classification and retrieval. Since these types of data are inherently relational, we propose a model that explicitly accounts for the interdependencies between images sharing common properties. We model the task as a binary labeling problem on a network, and use structured learning techniques to learn model parameters. We find that social-network metadata are useful in a variety of classification tasks, in many cases outperforming methods based on image content.