We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
An anytime algorithm is capable of returning a response to the given task at essentially any time; typically the quality of the response improves as the time increases. Here, we c...
Next to prediction accuracy, the interpretability of models is one of the fundamental criteria for machine learning algorithms. While high accuracy learners have intensively been e...
This work is about scene interpretation in the sense of detecting and localizing instances from multiple object classes. We concentrate on object indexing: generate an over-comple...
The biological immune system is an intricate network of specialized tissues, organs, cells, and chemical molecules. T-cell-dependent humoral immune response is one of the complex i...