← authors · overview

• A ConvNet for the 2020s
  2022 · 7082 citations
• Spatiotemporal Residual Networks for Video Action Recognition
  2016 · 494 citations
• VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
  2021 · 405 citations
• Convolutional Two-Stream Network Fusion for Video Action Recognition
  2016 · 373 citations
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
  2021 · 211 citations
• VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
  2021 · 90 citations
• Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
  2023 · 61 citations
• Multiscale Vision Transformers
  2021 · 56 citations
• Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
  2021 · 49 citations
• Long-Term Feature Banks for Detailed Video Understanding
  2018 · 33 citations
• MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
  2021 · 29 citations
• Masked Feature Prediction for Self-Supervised Visual Pre-Training
  2021 · 25 citations
• TrackFormer: Multi-Object Tracking with Transformers
  2021 · 6 citations
• 3D human pose estimation in video with temporal convolutions and semi-supervised training
  2018 · 5 citations
• Diffusion Models as Masked Autoencoders
  2023 · 2 citations