3 papers
cs.SD2020
Playing a Part: Speaker Verification at the Movies
Andrew Brown, Jaesung Huh, Arsha Nagrani +2
The goal of this work is to investigate the performance of popular speaker recognition models on speech segments from movies, where often actors intentionally disguise their voice…
cs.CV2020
Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
Andrew Brown, Weidi Xie, Vicky Kalogeiton +1
Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly…
cs.CV2020
Condensed Movies: Story Based Retrieval with Contextual Embeddings
Max Bain, Arsha Nagrani, Andrew Brown +1
Our objective in this work is long range understanding of the narrative structure of movies. Instead of considering the entire movie, we propose to learn from the `key scenes' of t…