Text and image subject classifiers: dense works better

We investigate the feasibility of training visual concept detectors for such abstract subject categories as biology and history with the aim of employing these for full-text to image linking. We show that using dense sampling methods can lead to image classifiers that perform well enough for interactive search. Echoing this dense sampling in the image domain, we also show that using term frequencies as text features outperforms using a topic abstraction method. Finally, we use these monomodal classifiers for the task of linking texts to images, improving more than 50% over the state-of-the-art, thereby showing that dense is better.