This paper describes an online learning method of color transformation for interactive object recognition. In order to recognize objects under various lighting conditions, the sys...
This paper presents a new kernel method for appearance-based object recognition, highly robust to noise and occlusion. It consists of a fully connected Markov Random Field that in...
Multiframe super-resolution (SR) reconstruction of small moving objects against a cluttered background is difficult for two reasons: a small object consists completely of "mix...
Adam W. M. van Eekeren, Klamer Schutte, Lucas J. v...
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
We present a method for automatically learning discriminative image patches for the recognition of given object classes. The approach applies discriminative training of log-linear...