Multi-camera tracking systems often must maintain consistent identity labels of the targets across views to recover 3D trajectories and fully take advantage of the additional info...
Abstract. Movies and TV are a rich source of diverse and complex video of people, objects, actions and locales "in the wild". Harvesting automatically labeled sequences o...
Timothee Cour, Chris Jordan, Eleni Miltsakaki, Ben...
We study the potential benefits to classification prediction that arise from having access to unlabeled samples. We compare learning in the semi-supervised model to the standard, ...
This paper introduces a novel method for obtaining increased predictive performance from transparent models in situations where production input vectors are available when building...
Creating more fine-grained annotated data than previously relevent document sets is important for evaluating individual components in automatic question answering systems. In this...