GuessWhat?! Visual object discovery through multi-modal dialogue

Abstract : We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. The goal of the game is to locate an unknown object in a rich image scene by asking a sequence of questions. Higher-level image understanding, like spatial reasoning and language grounding, is required to solve the proposed task. Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images. We explain our design decisions in collecting the dataset and introduce the oracle and questioner tasks that are associated with the two players of the game. We prototyped deep learning models to establish initial base-lines of the introduced tasks.
Type de document :
Communication dans un congrès
Conference on Computer Vision and Pattern Recognition, Jul 2017, Honolulu, United States. 〈http://cvpr2017.thecvf.com/〉
Liste complète des métadonnées

Littérature citée [48 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01549641
Contributeur : Florian Strub <>
Soumis le : mercredi 28 juin 2017 - 23:35:00
Dernière modification le : jeudi 11 janvier 2018 - 06:27:32

Fichier

1611.08481.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

  • HAL Id : hal-01549641, version 1
  • ARXIV : 1611.08481

Collections

Citation

Harm De Vries, Florian Strub, Sarath Chandar, Olivier Pietquin, Hugo Larochelle, et al.. GuessWhat?! Visual object discovery through multi-modal dialogue. Conference on Computer Vision and Pattern Recognition, Jul 2017, Honolulu, United States. 〈http://cvpr2017.thecvf.com/〉. 〈hal-01549641〉

Partager

Métriques

Consultations de la notice

168

Téléchargements de fichiers

59