← authors · overview

• Deformable Convolutional Networks
  2017 · 6915 citations
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
  2016 · 3439 citations
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
  2020 · 1868 citations
• Vision Transformer Adapter for Dense Predictions
  2022 · 205 citations
• Flow-Guided Feature Aggregation for Video Object Detection
  2017 · 105 citations
• Relation Networks for Object Detection
  2017 · 67 citations
• Instance-sensitive Fully Convolutional Networks
  2016 · 62 citations
• ConvMAE: Masked Convolution Meets Masked Autoencoders
  2022 · 52 citations
• Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
  2018 · 49 citations
• Decoupled Spatial-Temporal Transformer for Video Inpainting
  2021 · 47 citations
• Fully Convolutional Instance-aware Semantic Segmentation
  2016 · 38 citations
• Towards High Performance Video Object Detection for Mobiles
  2018 · 35 citations
• Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
  2022 · 18 citations
• Fast Convergence of DETR with Spatially Modulated Co-Attention
  2021 · 13 citations
• Learning Region Features for Object Detection
  2018 · 11 citations