← authors · overview

• Grounding DINO: Marrying DINO With Grounded Pre-training For Open-set Object Detection
  2023 · 1343 citations
• Vinvl: Revisiting Visual Representations In Vision-language Models
  2021 · 712 citations
• Regionclip: Region-based Language-image Pretraining
  2021 · 490 citations
• Neural Baby Talk
  2018 · 319 citations
• Multi-scale Vision Longformer: A New Vision Transformer For High-resolution Image Encoding
  2021 · 232 citations