Automatic annotation is an elegant alternative to explicit recognition in images. In annotation, the image is matched with keyword models, and the most relevant keywords are assig...
We present an efficient method for feature correspondence and object-based image matching, which exploits both photometric similarity and pairwise geometric consistency from local ...
Minsu Cho (Seoul National University), Jungmin Lee...
Active Appearance Models (AAMs) have been popularly used to represent the appearance and shape variations of human faces. Fitting an AAM to images recovers the face pose as well a...
Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiplescale mu...
We introduce a new EM framework in which it is possible not only to optimize the model parameters but also the number of model components. A key feature of our approach is that we...