We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
Abstract--Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot learning. To be effective, action learning should not be limited to direct replic...
— Many modern computer vision algorithms are built atop of a set of low-level feature operators (such as SIFT [1], [2]; HOG [3], [4]; or LBP [5], [6]) that transform raw pixel va...
Complex model editing activities are frequently performed to realize various model evolution tasks (e.g., model scalability, weaving aspects into models, and model refactoring). In...
Yu Sun, Jeff Gray, Christoph Wienands, Michael Gol...
We propose a framework for large scale learning and annotation of structured models. The system interleaves interactive labeling (where the current model is used to semiautomate t...