by Martina Megaro | Nov 4, 2019 | Video Processing, Visual Computing
Deep Generative Video Compression We propose an end-to-end, deep probabilistic modeling approach to compress low-resolution videos. Our approach builds upon variational autoencoder (VAE) models for sequential data and combines them with recent work on neural image...
by Martina Megaro | Dec 16, 2018 | VFX, Visual Computing
Incremental Acquisition and Reuse of Multimodal Affective Behaviors in a Conversational Agent We explore a way to elicit and evaluate affective behavior using crowdsourcing. We show that untrained crowd workers are able to author content for a broad variety of...
by Martina Megaro | Oct 1, 2018 | Robotics
Closed-Loop Temperature Control of Nylon Artificial Muscles We demonstrate a nested controller using temperature and position feedback to improve contraction speed, and investigate the cooling rates of various configurations that increase total force output. October...
by Martina Megaro | Jul 13, 2018 | Machine Learning, Story Technology, Video Processing, Visual Computing
Disentangled Sequential Autoencoder In our experiments on artificially generated cartoon video clips and voice recordings, we show that we can convert the content of a given sequence into another one by such content swapping. July 13, 2018International Conference on...
by Martina Megaro | Jul 11, 2018 | Machine Learning
Improving Optimization in Models with Continuous Symmetry Breaking We propose a new optimization algorithm that speeds up convergence using ideas from gauge theory in physics. July 11, 2018International Conference on Machine Learning (ICML) 2018 Authors Robert...
