Faces In Places: Compound query retrieval

Abstract : The goal of this work is to retrieve images containing both a target person and a target scene type from a large dataset of images. At run time this compound query is handled using a face classifier trained for the person, and an image classifier trained for the scene type. We make three contributions: first, we propose a hybrid convolutional neural network architecture that produces place-descriptors that are aware of faces and their corresponding descriptors. The network is trained to correctly classify a combination of face and scene classifier scores. Second, we propose an image synthesis system to render high quality fully-labelled face-and-place images, and train the network only from these synthetic images. Last, but not least, we collect and annotate a dataset of real images containing celebrities in different places, and use this dataset to evaluate the retrieval system. We demonstrate significantly improved retrieval performance for compound queries using the new face-aware place-descriptors.
Type de document :
Communication dans un congrès
BMVC - 27th British Machine Vision Conference, Sep 2016, York, United Kingdom. BMVC - 27th British Machine Vision Conference
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01353886
Contributeur : Relja Arandjelović <>
Soumis le : lundi 15 août 2016 - 23:53:27
Dernière modification le : jeudi 26 avril 2018 - 10:29:12
Document(s) archivé(s) le : mercredi 16 novembre 2016 - 10:20:19

Fichier

zhong16.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01353886, version 1

Collections

Citation

Yujie Zhong, Relja Arandjelović, Andrew Zisserman. Faces In Places: Compound query retrieval. BMVC - 27th British Machine Vision Conference, Sep 2016, York, United Kingdom. BMVC - 27th British Machine Vision Conference. 〈hal-01353886〉

Partager

Métriques

Consultations de la notice

433

Téléchargements de fichiers

262