• Publications
  • Influence
Learning to Count Objects in Natural Images for Visual Question Answering
TLDR
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. Expand
  • 111
  • 20
  • PDF
Privacy-aware image classification and search
TLDR
We learn privacy classifiers trained on a large set of manually assessed Flickr photos, combining textual metadata of images with a variety of visual features to enable privacy-oriented image search. Expand
  • 87
  • 17
  • PDF
T-REx: A Large Scale Alignment of Natural Language with Knowledge Base Triples
TLDR
We present T-REx, a dataset of large scale alignments between Wikipedia abstracts and Wikidata triples. Expand
  • 38
  • 15
  • PDF
Analyzing and predicting sentiment of images on the social web
TLDR
In this paper we study the connection between sentiment of images expressed in metadata and their visual content in the social photo sharing environment Flickr. Expand
  • 143
  • 12
  • PDF
Examination of isomer specific bioaccumulation parameters and potential in vivo hepatic metabolites of syn- and anti-Dechlorane Plus isomers in juvenile rainbow trout (Oncorhynchus mykiss).
Juvenile rainbow trout (Oncorhynchus mykiss) were exposed in the laboratory to elevated doses of syn- and anti-isomers of Dechlorane Plus (DP) via their diet for 49 days (uptake phase), followed byExpand
  • 97
  • 10
OpenIMAJ and ImageTerrier: Java libraries and tools for scalable multimedia analysis and indexing of images
TLDR
OpenIMAJ and ImageTerrier are recently released open-source libraries and tools for experimentation and development of multimedia applications using Java-compatible programming languages. Expand
  • 73
  • 10
  • PDF
Deep Set Prediction Networks
TLDR
We propose a general model for predicting sets that properly respects the structure of sets and avoids discontinuity issues as a result. Expand
  • 20
  • 10
  • PDF
Trophodynamics of some PFCs and BFRs in a western Canadian Arctic marine food web.
The trophodynamics of per- and polyfluorinated compounds and bromine-based flame retardants were examined in components of a marine food web from the western Canadian Arctic. The animals studied andExpand
  • 113
  • 9
Mind the gap: another look at the problem of the semantic gap in image retrieval
TLDR
This paper attempts to review and characterise the problem of the semantic gap in image retrieval and the attempts being made to bridge it. Expand
  • 175
  • 9
  • PDF
An object-based convolutional neural network (OCNN) for urban land use classification
TLDR
A novel object-based convolutional neural network is proposed for urban land use classification using VFSR images. Expand
  • 127
  • 9
  • PDF