Problem with the new version of the theme. about hugo_theme_adam_eve HOT 9 CLOSED

baseURL = "https://wsoda.telecom-paristech.fr/"
theme = "hugo_theme_adam_eve"
DefaultContentLanguage = "en"

[Languages]
[Languages.en]
languageCode = "en"
title = "Weakly Supervised Object Detection in Artworks"

[Languages.en.params]
description = ""

[[Languages.en.menu.main]]
    name = "Homepage"
    pre = "<span class='homepage'>⌂</span>"
    weight = -110
    identifier = "homepage"
    url = "/"

---
title: "Project page"
date: 2019-09-20T13:47:13+02:00
draft: false
---

[Nicolas Gonthier](https://perso.telecom-paristech.fr/gonthier/), [Yann Gousseau](https://perso.telecom-paristech.fr/gousseau/), [Said Ladjal](https://perso.telecom-paristech.fr/ladjal/), [Olivier Bonfait](http://tristan.u-bourgogne.fr/CGC/chercheurs/Bonfait/Olivier_Bonfait.html)

[Telecom ParisTech](https://www.telecom-paristech.fr/), [Universite Paris-Saclay](https://www.universite-paris-saclay.fr/en), [Universite de Bourgogne](http://en.u-bourgogne.fr/)

[VISART IV Where Computer Vision Meets Art ECCV 2018 Workshop](https://visarts.eu/)

<div id="banner" style="overflow: hidden; display: flex; justify-content:space-around;">
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="images/Q27896612_Regions_over075.jpg" height=350>
        </div>
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="images/Q743787_Regions_over075.jpg" height=350>
        </div>
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="images/Q28059074_Regions_over075.jpg" height=350>
        </div>
</div>
<div id="banner" style="overflow: hidden; display: flex; justify-content:space-around;">
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="images/Q18572427_Regions_over075.jpg" height=350>
        </div>
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="images/Q6043567_Regions_over075.jpg" height=350>
        </div>
</div>

Some detection results from our IconArt dataset.

# Abstract

We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task to manually marking objects. We show on several databases that dropping the instance-level annotations only yields mild performance losses. We also introduce a new database, IconArt, on which we perform detection experiments on classes that could not be learned on photographs, such as Jesus Child or Saint Sebastian. To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings. We believe that such a method is of great benefit for helping art historians to explore large digital databases. 

# Downloads

  * [Paper](https://arxiv.org/pdf/1810.02569.pdf)
  * [ArXiv](https://arxiv.org/abs/1810.02569)
  * [Dataset]({{< ref "dataset.md" >}})
  * [Code](https://github.com/nicaogr/Mi_max)
  * [Presentation](https://wsoda.telecom-paristech.fr/pdf/VISART_2018_slides.pdf)
    

# Publication

    Nicolas Gonthier, Yann Gousseau, Said Ladjal, Olivier Bonfait
    Weakly Supervised Object Detection in Artworks
    Workshop on Computer Vision for Art Analysis, ECCV, 2018.

# BibTex reference 

	@InProceedings{Gonthier18,
 	 author       = "Gonthier, N. and Gousseau, Y. and Ladjal, S. and Bonfait, O.",
 	 title        = "Weakly Supervised Object Detection in Artworks",
	 booktitle    = "Computer Vision -- ECCV 2018 Workshops",
	 year         = "2018",
         publisher    = "Springer International Publishing",
         pages        = "692--709"
	}

# Acknowledgments

This work is supported by the "IDI 2017" project funded by the IDEX Paris-Saclay, ANR-11-IDEX-0003-02.

<div id="banner" style="overflow: hidden; display: flex; justify-content:space-around;">
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="logo/leadImage.png" height=100>
        </div>
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="logo/ParisSaclay_Logo.jpg" height=100>
        </div>
        <div class="" style="max-width: 100%;max-height: 100%;display: inline-block;">
            <img src="logo/Investissements_d_avenir_logo.jpeg" height=100>
        </div>
</div>