← authors · overview

• VoxCeleb2: Deep Speaker Recognition
  2018 · 2259 citations
• Synthetic Data For Text Localisation In Natural Images
  2016 · 1532 citations
• The Conversation: Deep Audio-Visual Speech Enhancement
  2018 · 46 citations
• Object discovery and representation networks
  2022 · 6 citations
• Disentangled Speech Embeddings using Cross-modal Self-supervision
  2020 · 5 citations
• Efficiently Reconstructing Dynamic Scenes One D4RT at a Time
  2025
• Multi-task Self-Supervised Visual Learning
  2017
• Detect to Track and Track to Detect
  2017
• Exploiting temporal context for 3D human pose estimation in the wild
  2019
• Self-supervised learning of class embeddings from video
  2019
• Co-Attention for Conditioned Image Matching
  2020
• Self-Supervised Learning of Audio-Visual Objects from Video
  2020
• Slow-Fast Auditory Streams For Audio Recognition
  2021