Search Results for author:
Found 11 papers, 5 papers with code
Predicting User Annoyance Using Visual Attributes
In human-centric applications, some mistakes are more annoying to users than others.
Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes
Our approach produces a diverse set of plausible hypotheses for both semantic segmentation and prepositional phrase attachment resolution that are then jointly reranked to select the most consistent pair.
Question Relevance in VQA: Identifying Non-Visual And False-Premise Questions
We introduce the novel problem of determining the relevance of questions to images in VQA.
Radiation Search Operations using Scene Understanding with Autonomous UAV and UGV
Autonomously searching for hazardous radiation sources requires the ability of the aerial and ground systems to understand the scene they are scouting.
Functional Map of the World
We present an analysis of the dataset along with baseline approaches that reason about metadata and temporal views.
Semantic Stereo for Incidental Satellite Images
The increasingly common use of incidental satellite images for stereo reconstruction versus rigidly tasked binocular or trinocular coincident collection is helping to enable timely global-scale 3D mapping; however, reliable stereo correspondence from multi-date image pairs remains very challenging due to seasonal appearance differences and scene change.
Estimating Displaced Populations from Overhead
We introduce a deep learning approach to perform fine-grained population estimation for displacement camps using high-resolution overhead imagery.
Learning Geocentric Object Pose in Oblique Monocular Images
An object's geocentric pose, defined as the height above ground and orientation with respect to gravity, is a powerful representation of real-world structure for object detection, segmentation, and localization tasks using RGBD images.
Towards Indirect Top-Down Road Transport Emissions Estimation
In this work, we develop machine learning models that use satellite imagery to perform indirect top-down estimation of road transport emissions.
Single View Geocentric Pose in the Wild
Current methods for Earth observation tasks such as semantic mapping, map alignment, and change detection rely on near-nadir images; however, often the first available images in response to dynamic world events such as natural disasters are oblique.
