← authors · overview

• Cswin Transformer: A General Vision Transformer Backbone With Cross-shaped Windows
  2021 · 1069 citations
• Dynamic Head: Unifying Object Detection Heads With Attentions
  2021 · 847 citations
• Rethinking Classification And Localization For Object Detection
  2019 · 601 citations
• Mobile-former: Bridging Mobilenet And Transformer
  2021 · 583 citations
• Regionclip: Region-based Language-image Pretraining
  2021 · 490 citations