English

Learnable PINs: Cross-Modal Embeddings for Person Identity

Computer Vision and Pattern Recognition 2018-07-27 v2

Abstract

We propose and investigate an identity sensitive joint embedding of face and voice. Such an embedding enables cross-modal retrieval from voice to face and from face to voice. We make the following four contributions: first, we show that the embedding can be learnt from videos of talking faces, without requiring any identity labels, using a form of cross-modal self-supervision; second, we develop a curriculum learning schedule for hard negative mining targeted to this task, that is essential for learning to proceed successfully; third, we demonstrate and evaluate cross-modal retrieval for identities unseen and unheard during training over a number of scenarios and establish a benchmark for this novel task; finally, we show an application of using the joint embedding for automatically retrieving and labelling characters in TV dramas.

Keywords

Cite

@article{arxiv.1805.00833,
  title  = {Learnable PINs: Cross-Modal Embeddings for Person Identity},
  author = {Arsha Nagrani and Samuel Albanie and Andrew Zisserman},
  journal= {arXiv preprint arXiv:1805.00833},
  year   = {2018}
}

Comments

To appear in ECCV 2018

R2 v1 2026-06-23T01:42:52.346Z