← authors · overview

• Howto100m: Learning A Text-video Embedding By Watching Hundred Million Narrated Video Clips
  2019 · 721 citations
• Thinking Fast And Slow: Efficient Text-to-visual Retrieval With Transformers
  2021 · 104 citations
• Deep Metric Learning Beyond Binary Supervision
  2019 · 82 citations
• Learning A Text-video Embedding From Incomplete And Heterogeneous Data
  2018
• Training Vision Transformers For Image Retrieval
  2021