← authors · overview

• End-to-end representation learning for Correlation Filter based tracking
  2017 · 1515 citations
• Pixelwise Instance Segmentation with a Dynamically Instantiated Network
  2017 · 245 citations
• Holistic, Instance-Level Human Parsing
  2017 · 23 citations
• Fully-Convolutional Siamese Networks for Object Tracking
  2016 · 22 citations
• Incremental Tube Construction for Human Action Detection
  2017 · 12 citations
• Fully-Trainable Deep Matching
  2016 · 10 citations
• Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
  2017 · 8 citations
• Cross-modal Deep Face Normals with Deactivable Skip Connections
  2020 · 8 citations
• Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
  2021 · 3 citations
• Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos
  2016
• ROAM: a Rich Object Appearance Model with Application to Rotoscoping
  2016
• Devon: Deformable Volume Network for Learning Optical Flow
  2018
• R$^3$SGM: Real-time Raster-Respecting Semi-Global Matching for Power-Constrained Systems
  2018