Areas of Attention for Image Captioning

Abstract : We propose ``Areas of Attention'', a novel attention-based model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attention-based approaches that associate image regions only to the RNN state, our method allows a direct association between caption words and image regions. During training these associations are inferred from image-level captions, akin to weakly-supervised object detector training. These associations help to improve captioning by localizing the corresponding regions during testing. We also propose and compare different ways of generating attention areas: CNN activation grids, object proposals, and spatial transformers nets applied in a convolutional fashion. Spatial transformers give the best results. They allow for image specific attention areas, and can be trained jointly with the rest of the network. Our attention mechanism and spatial transformer attention areas together yield state-of-the-art results on the MSCOCO dataset.
Type de document :
Communication dans un congrès
ICCV - International Conference on Computer Vision, Oct 2017, Venice, Italy
Liste complète des métadonnées

Littérature citée [51 références]  Voir  Masquer  Télécharger
Contributeur : Thoth Team <>
Soumis le : vendredi 25 août 2017 - 16:06:00
Dernière modification le : mercredi 11 avril 2018 - 01:57:58


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01428963, version 2


Marco Pedersoli, Thomas Lucas, Cordelia Schmid, Jakob Verbeek. Areas of Attention for Image Captioning. ICCV - International Conference on Computer Vision, Oct 2017, Venice, Italy. 〈hal-01428963v2〉



Consultations de la notice


Téléchargements de fichiers