by Martina Megaro | Aug 6, 2017 | Machine Learning
Coordinated Multi-Agent Imitation Learning We propose a joint approach that simultaneously learns a latent coordination model along with the individual policies. August 6, 2017International Conference on Machine Learning (ICML) 2017 Authors Hoang Le...
by Martina Megaro | Jul 22, 2017 | Machine Learning, Story Technology, Visual Computing
Factorized Variational Autoencoders for Modeling Audience Reactions to Movies In this paper, we study non-linear tensor factorization methods based on deep variational autoencoders. July 22, 2017IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017...
by Martina Megaro | Jul 22, 2017 | Machine Learning, Video Processing, Visual Computing
One-Shot Metric Learning for Person Re-identification The proposed one-shot learning achieves performance that is competitive with supervised methods but uses only a single example rather than the hundreds required for the fully supervised case. July 22, 2017IEEE...
by Martina Megaro | Jul 21, 2017 | AR/VR, Machine Learning, Story Technology, Visual Computing
Weakly-supervised Visual Grounding of Phrases with Linguistic Structures We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention...
by Martina Megaro | Jul 20, 2017 | Animation, Story Technology
A Deep Learning Approach for Generalized Speech Animation We introduce a simple and effective deep learning approach to automatically generate natural looking speech animation that synchronizes to input speech. July 20, 2017ACM SIGGRAPH 2017 Authors Sarah...
