← authors · overview

• All Tokens Matter: Token Labeling for Training Better Vision Transformers
  2021 · 142 citations
• Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
  2022 · 73 citations
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
  2018 · 45 citations
• Multi-View Image Generation from a Single-View
  2017 · 41 citations
• Understanding The Robustness in Vision Transformers
  2022 · 34 citations
• Few-shot Object Detection via Feature Reweighting
  2018 · 17 citations
• Transferable Semi-supervised Semantic Segmentation
  2017 · 15 citations
• Object Relation Detection Based on One-shot Learning
  2018 · 14 citations
• Video-based Person Re-identification with Accumulative Motion Context
  2017 · 13 citations
• Multi-Fiber Networks for Video Recognition
  2018 · 13 citations
• MagicEdit: High-Fidelity and Temporally Coherent Video Editing
  2023 · 11 citations
• Shunted Self-Attention via Multi-Scale Token Aggregation
  2021 · 10 citations
• Classification Calibration for Long-tail Instance Segmentation
  2019 · 9 citations
• Contrastive Masked Autoencoders are Stronger Vision Learners
  2022 · 8 citations
• Multi-stage Object Detection with Group Recursive Learning
  2016 · 6 citations