We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Give...
We present a generic objectness measure, quantifying how
likely it is for an image window to contain an object of
any class. We explicitly train it to distinguish objects with
a...
Pierre America, Robin Milner, Oscar Nierstrasz, Ma...
Psychologists have proposed that many human-object interaction activities form unique classes of scenes. Recognizing these scenes is important for many social functions. To enable...
Identifying handled objects, i.e. objects being manipulated by a user, is essential for recognizing the person’s activities. An egocentric camera as worn on the body enjoys many...
We propose an efficient method, built on the popular Bag
of Features approach, that obtains robust multiclass pixellevel
object segmentation of an image in less than 500ms,
with...
David Aldavert, Arnau Ramisa, Ricardo Toledo, Ramo...