← authors · overview

• Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning
  2017 · 22 citations
• Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
  2016 · 13 citations
• TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
  2021 · 12 citations
• Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors
  2022 · 12 citations
• Temporal Gaussian Mixture Layer for Videos
  2018 · 9 citations
• Video + CLIP Baseline for Ego4D Long-term Action Anticipation
  2022 · 7 citations
• Identifying First-person Camera Wearers in Third-person Videos
  2017 · 5 citations
• ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
  2021 · 2 citations
• Video Question Answering with Iterative Video-Text Co-Tokenization
  2022 · 2 citations
• Forecasting Hands and Objects in Future Frames
  2017 · 1 citations
• CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings
  2025
• Grafting Vision Transformers
  2022
• AAN: Attributes-Aware Network for Temporal Action Detection
  2023
• Language Repository for Long Video Understanding
  2024