by Sarah Frigg | Mar 7, 2016 | Machine Learning, Visual Computing
Assessing Tracking Performance in Complex Scenarios using Mean Time Between Failures In this work we propose ‘mean time between failures’ as a viable summary of solution quality — especially when the goal is to follow objects for as long as possible March 7,...
by Sarah Frigg | Mar 7, 2016 | Machine Learning, Visual Computing
Person Re-identification using Deformable Patch Metric Learning In this paper, we propose to learn appearance measures for patches that are combined using a spring model for addressing the correspondence problem. March 7, 2016IEEE Winter Conference on Applications...
by Sarah Frigg | Mar 7, 2016 | Machine Learning
Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval We showcase the efficacy of our approach in a user study, where we demonstrate orders-of-magnitude improvements in search quality compared to baseline systems March 7, 2016Intelligent User...
by Sarah Frigg | Feb 12, 2016 | Machine Learning, Visual Computing
Exploiting View-Specific Appearance Similarities Across Classes for Zero-shot Pose Prediction: A Metric Learning Approach We propose a metric learning approach for joint class prediction and pose estimation. February 12, 2016Association for the Advancement of...
by Sarah Frigg | Dec 12, 2015 | Machine Learning, Visual Computing
Smooth Imitation Learning We study the problem of smooth imitation learning, where the goal is to train a policy that can imitate human behavior in a dynamic and continuous environment. December 12, 2015Neural Information Processing Systems (NIPS) 2015 ...
