Illustrate your travel notes: web-based story visualization.

In this paper, we present an automatic web-based framework to insert images to the proper location of travel notes without restrictions on pre-defined vocabulary and training process. Instead of learning region-entity correspondences from explicitly human labelling, we collected weakly labeled Web images and proposed a method based on clustering to further discover image regions whose visual contents are highly correlated with the corresponding weak labels, from the original whole images. Then an adaptive visual representation is constructed from the discovered image regions which can automatically link phrase-image pairs. We also release a new dataset TVN25 targeting at Web-based travel notes visualization task which consists of 25 travel notes and over 22k weakly labeled Web images about the lingual phrases in travel notes. Experiments results on travel notes visualization not only demonstrated the effectiveness of our proposed framework, but also show the potential for more real-world applications.