Search
Now showing items 1-10 of 58
EM, MCMC, and Chain Flipping for Structure from Motion with Unknown Correspondence
(Georgia Institute of Technology, 2003)
Learning spatial models from sensor data raises the challenging data association
problem of relating model parameters to individual measurements. This paper proposes an
EM-based algorithm, which solves the model learning ...
A computational framework for unsupervised analysis of everyday human activities
(Georgia Institute of Technology, 2008-07-07)
In order to make computers proactive and assistive, we must enable them to perceive, learn, and predict what is happening in their surroundings. This presents us with the challenge of formalizing computational models of ...
What Are the Ants Doing? Vision-Based Tracking and Reconstruction of Control Programs
(Georgia Institute of Technology, 2005-04)
In this paper, we study the problem of going
from a real-world, multi-agent system to the generation of
control programs in an automatic fashion. In particular,
a computer vision system is presented, capable of ...
Deep Segments: Comparisons between Scenes and their Constituent Fragments using Deep Learning
(Georgia Institute of Technology, 2014-09)
We examine the problem of visual scene understanding and abstraction from first person video. This is an important problem and successful approaches would enable complex scene characterization tasks that go beyond ...
A Visualization Framework for Team Sports Captured using Multiple Static Cameras
(Georgia Institute of Technology, 2013)
We present a novel approach for robust localization of multiple people observed using a set of static cameras. We use this
location information to generate a visualization of the virtual offside line in soccer games. To ...
Modeling structured activity to support human-robot collaboration in the presence of task and sensor uncertainty
(Georgia Institute of Technology, 2013-11)
A representation for structured activities is developed that allows a robot to probabilistically infer which task actions a human is currently performing and to predict which future actions will be executed and when they ...
Anticipating Human Actions for Collaboration in the Presence of Task and Sensor Uncertainty
(Georgia Institute of Technology, 2014-06)
A representation for structured activities is developed that allows a robot to probabilistically infer which task actions a human is currently performing and to predict which future actions will be executed and when they ...
Visually grounded language understanding and generation
(Georgia Institute of Technology, 2020-01-13)
The world around us involves multiple modalities -- we see objects, feel texture, hear sounds, smell odors and so on. In order for Artificial Intelligence (AI) to make progress in understanding the world around us, it needs ...
Building agents that can see, talk, and act
(Georgia Institute of Technology, 2020-04-25)
A long-term goal in AI is to build general-purpose intelligent agents that simultaneously possess the ability to perceive the rich visual environment around us (through vision, audition, or other sensors), reason and infer ...
Domain adaptation via data augmentation
(Georgia Institute of Technology, 2020-04-28)
Deep learning (DL) models require large labeled datasets for training. Practitioners often need to adapt an existing DL model to a different domain. For instance, a practitioner in a company developing autonomous vehicles ...