← authors · overview

• Protecting Celebrities from DeepFake with Identity Consistency Transformer
  2022 · 160 citations
• UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection
  2022 · 117 citations
• Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism
  2017 · 54 citations
• Coherent Online Video Style Transfer
  2017 · 39 citations
• Reduce Information Loss in Transformers for Pluralistic Image Inpainting
  2022 · 8 citations
• Decouple Learning for Parameterized Image Operators
  2018 · 7 citations
• Towards Generalizable and Robust Face Manipulation Detection via Bag-of-local-feature
  2021 · 7 citations
• Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation
  2022 · 5 citations
• Real-time Online Multi-Object Tracking in Compressed Domain
  2022 · 5 citations
• Memory-Based Neighbourhood Embedding for Visual Recognition
  2019 · 3 citations
• Improved Image Matting via Real-time User Clicks and Uncertainty Estimation
  2020 · 1 citations
• Temporal RoI Align for Video Object Recognition
  2021
• Transformer based Pluralistic Image Completion with Reduced Information Loss
  2024