Almut Sophia Koepke
Postdoctoral Researcher
a-sophia.koepke (at)


Almut Sophia Koepke is a post-doctoral researcher in the EML group where she works with Zeynep Akata. Prior to that, she completed her DPhil in the Visual Geometry Group (VGG) at the University of Oxford, supervised by Andrew Zisserman.

During her PhD, her research focussed on self-supervised learning and on audio-visual learning problems.


  • Audio retrieval with natural language queries

Andreea-Maria Oncescu*, A. Sophia Koepke*, Joao F. Henriques, Zeynep Akata, Samuel Albanie
Paper | Project page | Code


  • Distilling audio-visual knowledge by compositional contrastive learning

Yanbei Chen, Yongqin Xian, A. Sophia Koepke, Ying Shan, Zeynep Akata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Paper | Code


  • Sight to sound: An end-to-end approach for visual piano transcription

A. Sophia Koepke, Olivia Wiles, Yael Moses, Andrew Zisserman
The International Conference on Acoustics, Speech, & Signal Processing (ICASSP), 2020
Paper | Project page


  • Self-supervised learning of class embeddings from video

Olivia Wiles, A. Sophia Koepke, Andrew Zisserman
IEEE/CVF International Conference on Computer Vision Workshop (ICCV Workshop), 2019


  • Visual pitch estimation

A. Sophia Koepke, Olivia Wiles, Andrew Zisserman
Sound and Music Compution Conference (SMC), 2019
Paper | Project page


  • Self-supervised learning of a facial attribute embedding from video

Olivia Wiles*, A. Sophia Koepke*, Andrew Zisserman
British Machine Vision Conference (BMVC), 2018
Paper | Supplementary material | Project page | Code


  • X2Face: A network for controlling face generation by using images, audio, and pose codes

Olivia Wiles*, A. Sophia Koepke*, Andrew Zisserman
European Conference on Computer Vision (ECCV), 2018
Paper | Project page | Code


* denotes equal contribution