Daan T. J. Vreeswijk

Learn More
This paper investigates the natural bias humans display when labeling images with a container label like <i>vehicle</i> or <i>carnivore</i>. Using three container concepts as subtree root nodes, and all available concepts between these roots and the images from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset, we analyze the(More)
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(More)
  • 1