← authors · overview

• Semantic Understanding Of Scenes Through The ADE20K Dataset
  2016 · 1348 citations
• Voxformer: Sparse Voxel Transformer For Camera-based 3D Semantic Scene Completion
  2023 · 235 citations
• Action Recognition From Single Timestamp Supervision In Untrimmed Videos
  2019 · 54 citations
• Dmm-net: Differentiable Mask-matching Network For Video Object Segmentation
  2019 · 48 citations
• Pose Estimation For Objects With Rotational Symmetry
  2018 · 39 citations
• Socratic-mcts: Test-time Visual Reasoning By Asking The Right Questions
  2025
• Lyra: Generative 3D Scene Reconstruction Via Video Diffusion Model Self-distillation
  2025
• Radargen: Automotive Radar Point Cloud Generation From Cameras
  2025
• Sana-video: Efficient Video Generation With Block Linear Diffusion Transformer
  2025