Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
Human Activity Recognition with Metric Learning
This paper proposes a metric learning based approach for human activity recognition with two main objectives: (1) reject unfamiliar activities and (2) learn with few examples. We show that our…
View via Publisher
Utility data annotation with Amazon Mechanical Turk
TLDR
This work shows how to outsource data annotation to Amazon Mechanical Turk, and describes results for several different annotation problems, including some strategies for determining when the task is well specified and properly priced.
View on IEEE
Programmatic Gold: Targeted and Scalable Quality Assurance in Crowdsourcing
TLDR
This paper presents an automated quality assurance process that is inexpensive and scalable, and finds that it decreases the amount of manual work required to manage crowdsourced labor while improving the overall quality of the results.
View Paper
It's All About the Data
TLDR
Methods to prepare data, check quality, and set prices for work for this annotation process are described, which can be used to build a large and challenging labelled face dataset with no manual intervention.
View on IEEE
Efficient Unsupervised Learning for Localization and Detection in Object Categories
TLDR
A novel method for learning templates for recognition and localization of objects drawn from categories using a generative model that allows learning to be orders of magnitude faster than previous approaches while incorporating many more features.
View Paper
People helping robots helping people: Crowdsourcing for grasping novel objects
TLDR
This paper presents a framework for robot supervision through Amazon Mechanical Turk, where people provide semantic information about the world and subjective judgements and the robot autonomously utilizes the additional information to enhance its capabilities.
View on IEEE
Visualizing the History of Living Spaces
TLDR
A novel approach is proposed in which a large number of simple motion sensors and a small set of video cameras are used to monitor a large office space to help designers and managers of building systems gain access to information about occupants' behavior in the context of an entire building in a way that is only minimally intrusive to the occupants' privacy.
View on IEEE
Tracking people in mixed modality systems
TLDR
This paper describes a method that allows to evaluate when the tracking system is unreliable and present the data to a human operator for disambiguation, and presents an approach to tracking in mixed modality systems, with a variety of sensors.
View on SPIE
Designing a scalable crowdsourcing platform
TLDR
The approach to designing CrowdFlower - a scalable crowdsourcing platform - as it evolved over the last 4 years is described, including the development of "Gold standard" to block attempts of fraud.
View on ACM
SEMANTIC SCENE UNDERSTANDING FOR THE AUTONOMOUS PLATFORM
TLDR
A new multi-sensor platform for data collection and algorithm testing, with approaches for automatic camera and LiDAR calibration; three-dimensional scene reconstruction and odometry calculation; semantic segmentation that provides obstacle recognition and underlying surface classification; object detection; point cloud segmentation.
View PDF
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License