← authors · overview

• Pyramid Vision Transformer: A Versatile Backbone For Dense Prediction Without Convolutions
  2021 · 4239 citations
• How Far Are We To GPT-4V? Closing The Gap To Commercial Multimodal Models With Open-source Suites
  2024 · 339 citations
• PAN++: Towards Efficient And Accurate End-to-end Spotting Of Arbitrarily-shaped Text
  2021 · 100 citations
• Dynamic Sampling Networks For Efficient Action Recognition In Videos
  2020 · 76 citations
• Basictad: An Astounding Rgb-only Baseline For Temporal Action Detection
  2022 · 40 citations