• Reset your password

User account menu

  • Log in
Home
Image not available
Andreu Sulé

Main navigation

  • Home
  • What are my publications?
  • Who I am?
  • What I research?
  • What I teach?
  • Contact

Visual Genome or how computers can recognize what happens in an image

Breadcrumb

  • Home
  • Visual Genome or how computers can recognize what happens in an image
By sule | 5:35 PM CET, Thu February 11, 2016

Visual Genome

Image not available
Hello,

Automatic representation of images is one of the most challenges of the Computers and Classification sciences. Can computers recognize not just objects but to make sense of what’s actually going on in images?

The ability of to automatically recognize the contents of images is a discipline that is part of a major field called Computer Vision, and deep learning a method by virtue of which machines can learn to analyse and classify images.  This branch of Artificial Intelligence (AI) is based on a “set of algorithms that attempt to model high-level abstractions in data by using multiple processing layers with complex structures, or otherwise composed of multiple non-linear transformations”.

In this research framework is that we have to understand the Visual Genome project. Visual Genome is a dataset of 108,077 images developed by Fei-Fei Li, a professor who specializes in computer vision and who directs the Stanford Artificial Intelligence Lab, together with several colleagues.

The Visual Genome software, as other projects (e.g. Microsoft Common Objects in Context), tries to describe in a human way what happens in an image. In Fei-Fei Li’s words: “You’re sitting in an office, but what’s the layout, who’s the person, what is he doing, what are the objects around, what event is happening?”

The opportunities of this research are enormous, from self-driving cars understanding properly (not just seeing) what’s happen around them to robots that can interact with humans in a better way.

Enjoy it!

Andreu Sulé

University of Barcelona

Visual Genome
Images
Deep learning
Artificial intelligence
Andreu Sulé newsletter

categories

Search engines 1
Discovery tools 1
Libraries 8
Smartwatches 1
User interfaces 1
Web Usability 1
Education 1
Research 2
Seminars 1
Responsive web design 1
Google Glass 1
Semantic Web 4
Books 1
Cataloguing 1
Search 1
BOBCATSSS 2015 2
Conference 1
Information 1
Documentation 1
Lib 1
Sustainability 1
Google 2
SERP 1
Almetrics 1
OCLC 2
Library of Congress 1
linked data 6
Facultat de Biblioteconomia i Documentació 2
Big data 2
Marshall Breeding 1
NISO 1
Discovery technologies 1
Web pages 1
Ranking 1
III International Seminar on LIS Education and Research 1
Schema.org 1
Apple Watch 1
UX 1
Interfaces design 1
Entity linking 1
Drupal 1
Agri SA 1
Glòria Pérez-Salmerón 1
IFLA 1
Democracy 1
LodView 1
National Library of the Netherlands 1
ESWC 2016 1
Big Data Congress 1
Startup Grind Barcelona 1
Start-ups 1
Catalonia 1
Google Search 1
App 1
Metadata 1
Publishers 1
European Data Portal 1
Open data 1
Visual Genome 1
Imatges 1
Reconeixement automàtic 1
Intel·ligència artificial 1
Images 1
Deep learning 1
Artificial intelligence 1
RDF 2
Digital collections 1
Spain 1
Libhub Initiative 1
Zepheira 1
BIBFRAME 1
Catalogues 1
RDA 1
Michael Gorman 1
International Council on Archives 1
Archival description 1
Standards 1
BOBCATSSS 2017 1

Footer menu

  • Contact

Copyright © 2025 Andreu Sule - All rights reserved