Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
This paper introduces an approach for handling complex labelling problems driven by local constraints. The purpose is illustrated by two applications: detection of the road networ...
Abstract-- Extending traditional models for discriminative labeling of structured data to include higher-order structure in the labels results in an undesirable exponential increas...
Structured prediction tasks pose a fundamental trade-off between the need for model complexity to increase predictive power and the limited computational resources for inference i...
In the last decade, connectionist models have been proposed that can process structured information directly. These methods, which are based on the use of graphs for the representa...
Werner Uwents, Gabriele Monfardini, Hendrik Blocke...