Learning and Understanding a Disentangled Feature Representation for Hidden Parameters in Reinforcement Learning

no code implementations • 29 Nov 2022 • Christopher Reale, Rebecca Russell

We present an unsupervised method to map RL trajectories into a feature space where distance represents the relative difference in system behavior due to hidden parameters.

Metric Learning reinforcement-learning +1

Multivariate Uncertainty in Deep Learning

no code implementations • 31 Oct 2019 • Rebecca L. Russell, Christopher Reale

We experimentally show in a visual tracking problem the large impact that accurate multivariate uncertainty quantification can have on Kalman filter performance for both in-domain and out-of-domain evaluation data.

Autonomous Vehicles Pose Estimation +3

Can You Spot the Semantic Predicate in this Video?

no code implementations • COLING 2018 • Christopher Reale, Claire Bonial, Heesung Kwon, Clare Voss

We propose a method to improve human activity recognition in video by leveraging semantic information about the target activities from an expert-defined linguistic resource, VerbNet.

Human Activity Recognition Multi-Task Learning

Object and Text-guided Semantics for CNN-based Activity Recognition

no code implementations • 4 May 2018 • Sungmin Eum, Christopher Reale, Heesung Kwon, Claire Bonial, Clare Voss

We further improve upon the multitask learning approach by exploiting a text-guided semantic space to select the most relevant objects with respect to the target activities.

Human Activity Recognition Object Recognition