Computer Vision

We propose a novel object- and scene-based semantic fusion network and representation.

We propose a recurrent decision tree framework that can directly incorporate temporal consistency into a data-driven predictor, as well as a learning algorithm that can efficiently learn such temporally smooth models.

We propose a new approach based on finding latent Path Patterns in both real and simulated data in order to analyze and compare them.

We propose a system for painting large-scale murals of arbitrary input photographs.

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.

We propose a metric learning approach for joint class prediction and pose estimation.

We propose a method for reducing noise in images created by any tone mapping operator.

This paper discusses the benefits and tradeoffs between agent-centric and event-centric approaches towards authoring the domain knowledge of story worlds.