A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
A novel method unifying viewer and model centered approaches for representing structurally complex 3-D objects like human faces is presented. The uni ed 3D frequency-domain repres...
Objects in freely-drawn sketches often have no spatial or temporal separation, making object recognition difficult. We present a two-step stroke-grouping algorithm that first clas...
Eric Jeffrey Peterson, Thomas F. Stahovich, Eric D...
Nowadays, many applications need data modeling facilities for the description of complex objects with spatial and/or temporal facilities. Responses to such requirements may be fou...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...