Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels....
We introduce a new model for semantic annotation and retrieval from image databases. The new model is based on a probabilistic formulation that poses annotation and retrieval as c...
Abstract We present an active learning framework that predicts the tradeoff between the effort and information gain associated with a candidate image annotation, thereby ranking un...
Abstract. While there has been substantial progress in segmenting natural images, state-of-the-art methods that perform well in such tasks unfortunately tend to underperform when c...
While there has been substantial progress in segmenting natural im-
ages, state-of-the-art methods that perform well in such tasks unfortunately tend
to underperform ...
A. Lucchi, K. Smith, R. Achanta, V. Lepetit, P. Fu...