We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
Personal ontology construction is the task of sorting through relevant materials, identifying the main topics and concepts, and organizing them to suit personal needs. Automatic c...
While Active Learning (AL) has already been shown to markedly reduce the annotation efforts for many sequence labeling tasks compared to random selection, AL remains unconcerned a...
Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogue...
We present a new and efficient semi-supervised training method for parameter estimation and feature selection in conditional random fields (CRFs). In real-world applications suc...