← authors · overview

• Masked-attention Mask Transformer For Universal Image Segmentation
  2021 · 2664 citations
• Detecting Twenty-thousand Classes Using Image-level Supervision
  2022 · 465 citations
• In Defense Of Grid Features For Visual Question Answering
  2020 · 285 citations
• Self-supervised Pretraining Of 3D Features On Any Point-cloud
  2021 · 249 citations
• Flowvid: Taming Imperfect Optical Flows For Consistent Video-to-video Synthesis
  2023 · 36 citations