We propose to combine two approaches for modeling data admitting sparse representations: on the one hand, dictionary learning has proven effective for various signal processing ta...
Embedding generic shape information into probabilistic spatiotemporal video object segmentation is of pivotal importance to achieving better segmentation, since it provides valuab...
Most real-world data is stored in relational form. In contrast, most statistical learning methods work with "flat" data representations, forcing us to convert our data i...
Lise Getoor, Nir Friedman, Daphne Koller, Benjamin...
— A new hybrid motion planning technique based on Harmonic Functions (HF) and Probabilistic Roadmaps (PRM) is presented. The proposed approach consists of incrementally building ...
Most real-world data is heterogeneous and richly interconnected. Examples include the Web, hypertext, bibliometric data and social networks. In contrast, most statistical learning...