Gordon Christie

Learn More
Visual Question Answering (VQA) is the task of answering natural-language questions about images. We introduce the novel problem of determining the relevance of questions to images in VQA. Current VQA models do not reason about whether a question is even related to the given image (e.g. What is the capital of Argentina?) or if it requires information from(More)
Computer Vision algorithms make mistakes. In human-centric applications, some mistakes are more annoying to users than others. In order to design algorithms that minimize the annoyance to users, we need access to an annoyance or cost matrix that holds the annoyance of each type of mistake. Such matrices are not readily available, especially for a wide gamut(More)
We present an approach to simultaneously perform semantic segmen-tation and prepositional phrase attachment resolution for captioned images. The motivation for this work comes from the fact that some ambiguities in language simply cannot be resolved without simultaneously reasoning about an associated image. If we consider the sentence " I shot an elephant(More)
Autonomously searching for hazardous radiation sources requires the ability of the aerial and ground systems to understand the scene they are scouting. In this paper, we present systems, algorithms, and experiments to perform radiation search using unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV) by employing semantic scene segmentation.(More)
— Localization in a global map is critical to success in many autonomous robot missions. This is particularly challenging for multi-robot operations in unknown and adverse environments. Here, we are concerned with providing a small unmanned ground vehicle (UGV) the ability to localize itself within a 2.5D aerial map generated from imagery captured by a(More)
As rocks are transported along the conveyor belt of a quarry, the maximum dimension of the rocks exiting the crushers should not exceed a size threshold specific to each crusher. If the rocks are too large then they can pose a threat to equipment, and lead to a large cost in repair and loss of production. A 2D vision system is presented, which is capable of(More)
  • Derek Sleeman, Zhi Luo, Gordon Christie, George Coghill, Peter Andrews, Pat Jones
  • 2005
At the 1999 AIME Conference [1] we reported a decision tree study on a subset of data, including time series physiological data, admissions characteristics, and outcome after traumatic head injury. That study analysed total duration for which patients had, for example, raised Intracranial Pressure, but it did not consider temporal relationships between(More)
Model discovery systems are able to use collected domain data to either revise existing models (Prometheus), or create new models (Lagramge). However, these systems do not provide the ability to explicitly obtain and use feedback during model searches. Creating a system able to use this feedback explicitly would allow a user who was not entirely certain of(More)
  • 1