We present a methodology for the real time alignment of music signals using sequential Montecarlo inference techniques. The alignment problem is formulated as the state tracking o...
Abstract. Due to its great ability of conquering clutters, which is especially useful for high-dimensional tracking problems, particle filter becomes popular in the visual trackin...
In cross-modal inference, we estimate complete fields from noisy and missing observations of one sensory modality using structure found in another sensory modality. This inference...
S. Ravela, Antonio B. Torralba, William T. Freeman
In this paper we overview our recent work and outline our current line of research: First, we describe the WCSP framework and its related local consistencies. Second, the Max-SAT p...
Abstract. In this paper we unify divergence minimization and statistical inference by means of convex duality. In the process of doing so, we prove that the dual of approximate max...