← authors · overview

• Beyond Skip Connections: Top-down Modulation For Object Detection
  2016 · 337 citations
• Rethinking the Faster R-CNN Architecture for Temporal Action Localization
  2018 · 33 citations
• An Efficient 3D CNN for Action/Object Segmentation in Video
  2019 · 23 citations
• Learning Video Representations from Textual Web Supervision
  2020 · 16 citations
• The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
  2020 · 10 citations
• Relational Action Forecasting
  2019 · 7 citations
• Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows
  2020