Faces In Places: Compound query retrieval

Yujie Zhong (1) , Relja Arandjelovic (2, 3) , Andrew Zisserman (1)

1 VGG - Visual Geometry Group
2 WILLOW - Models of visual object recognition and scene understanding
3 LIENS - Laboratoire d'informatique de l'école normale supérieure

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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

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