← authors · overview

• Hidden Two-Stream Convolutional Networks for Action Recognition
  2017 · 99 citations
• Guided Optical Flow Learning
  2017 · 34 citations
• Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
  2023 · 21 citations
• Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
  2017 · 6 citations
• Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
  2021 · 5 citations
• RUC+CMU: System Report for Dense Captioning Events in Videos
  2018 · 4 citations
• Training-free Monocular 3D Event Detection System for Traffic Surveillance
  2020 · 4 citations
• Video Representation Learning and Latent Concept Mining for Large-scale Multi-label Video Classification
  2017 · 3 citations
• Pose Guided Person Image Generation with Hidden p-Norm Regression
  2021 · 2 citations
• Deep Local Video Feature for Action Recognition
  2017