• Publications
  • Influence
Learning to Map Nearly Anything
TLDR
We propose a cross-modal distillation strategy to learn to predict the distribution of fine-grained properties from overhead imagery, without requiring any manual annotation. Expand
  • 3
  • 1
  • PDF
A Multimodal Approach to Mapping Soundscapes
TLDR
We explore the problem of mapping soundscapes, that is, predicting the types of sounds that are likely to be heard at a given geographic location. Expand
  • 12
  • PDF
Analyzing human appearance as a cue for dating images
TLDR
We propose an approach, based on deep convolutional neural networks, to estimate when an image was captured directly from raw pixel intensities. Expand
  • 10
  • PDF
miR-15a: a potential diagnostic biomarker and a candidate for non-operative therapeutic modality for age-related cataract
ABSTRACT Introduction: In order to better understand the role of hsa-miR-15a in the pathogenesis of age-related cataracts, we hypothesised altered expression, and of target anti-apoptotic genes,Expand
  • 2
Learning Geo-Temporal Image Features
TLDR
We propose to implicitly learn to extract geo-temporal image features, which are mid-level features related to when and where an image was captured, by explicitly optimizing for a set of location and time estimation tasks. Expand
  • 4
  • PDF
Remote Estimation of Free-Flow Speeds
TLDR
We propose an automated method to estimate a road segment’s free-flow speed from overhead imagery and road meta-data. Expand
  • 3
  • PDF
Role of extracellular matrix remodelling gene SNPs in keratoconus
ABSTRACT Introduction: Single nucleotide polymorphisms (SNPs) in genes for certain structural components may be implicated in the pathogenesis of keratoconus. We hypothesized links between SNPs inExpand
  • 1
Learning to Map the Visual and Auditory World
TLDR
We use well-defined probabilistic models and a weakly-supervised, multi-task training strategy to estimate the expected visual and auditory ground-level attributes consisting of the type of scenes, objects, and sounds a person can experience at a location. Expand