• Publications
  • Influence
Wide-Area Image Geolocalization with Aerial Reference Imagery
tl;dr
We propose to use deep convolutional neural networks to address the problem of cross-view image geolocalization, in which the geolocation of a ground-level query image is estimated by matching to georeferenced aerial images. Expand
  • 108
  • 19
  • Open Access
Selecting Degenerate Multiplex PCR Primers
tl;dr
An iterative beam-search algorithm, Multiple, Iterative Primer Selector, is presented for the Multiple Degenerate Primer Design (MDPD) problem. Expand
  • 32
  • 11
  • Open Access
Manifold clustering
tl;dr
Manifold learning has become a vital tool in data driven methods for interpretation of video, motion capture data when they lie on a low dimensional, nonlinear manifold. Expand
  • 151
  • 8
  • Open Access
Deep Randomized Ensembles for Metric Learning
tl;dr
We propose a novel, generalizable and fast method to define a family of embedding functions that can be used as an ensemble to give improved results on image retrieval tasks. Expand
  • 46
  • 8
  • Open Access
Finding Waldo: Learning about Users from their Interactions
tl;dr
In this paper, we demonstrate that we can accurately predict a user's task performance and infer some user personality traits by using machine learning techniques to analyze interaction data. Expand
  • 96
  • 4
  • Open Access
Manifold learning for 4D CT reconstruction of the lung
tl;dr
We use a manifold learning algorithm to parameterize each slab data with respect to the breathing cycle, and coordinate these parameterizations for different sections of the lung. Expand
  • 38
  • 4
  • Open Access
Viewpoint Manifolds for Action Recognition
tl;dr
We present a framework for learning a compact representation of primitive actions (e.g., walk, punch, kick, sit) that can be used for video obtained from a single camera for simultaneous action recognition and viewpoint estimation. Expand
  • 29
  • 4
  • Open Access
A Survey of Manifold Learning for Images
tl;dr
This paper attempts to characterize the special features of manifold learning on image data sets, and to highlight the value and limitations of these approaches. Expand
  • 82
  • 2
  • Open Access
Learning the viewpoint manifold for action recognition
tl;dr
We present a framework for learning a compact representation of primitive actions (e.g., walk, punch, kick, sit) that can be used for video obtained from a single camera for simultaneous action recognition and viewpoint estimation. Expand
  • 93
  • 2
  • Open Access
Understanding and Mapping Natural Beauty
tl;dr
We provide methods for quantifying and predicting the scenicness of an image. Expand
  • 19
  • 2
  • Open Access