| Extending Video Masked Autoencoders to 128 frames | | 94.9 | LVMAE | 2024-11-20 |
| Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition | ✓ Link | 90.8 | Video-FocalNet-B | 2023-07-13 |
| AIM: Adapting Image Models for Efficient Video Action Recognition | ✓ Link | 90.6 | AIM (CLIP ViT-L/14, 32x224) | 2023-02-06 |
| Dual-path Adaptation from Image to Video Transformers | ✓ Link | 88.7 | DUALPATH | 2023-03-17 |
| TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning | | 88.3 | TFCNet | 2022-03-11 |
| Learning Correlation Structures for Vision Transformers | | 88.3 | StructVit-B-4-1 | 2024-04-05 |
| Object-Region Video Transformers | ✓ Link | 88.0 | ORViT TimeSformer | 2021-10-13 |
| Group Contextualization for Video Recognition | ✓ Link | 87.6 | GC-TDN | 2022-03-18 |
| BEVT: BERT Pretraining of Video Transformers | ✓ Link | 86.7 | BEVT | 2021-12-02 |
| Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition | ✓ Link | 86 | PSB | 2022-07-27 |
| VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning | ✓ Link | 85.5 | VIMPAC | 2021-06-21 |
| Relational Self-Attention: What's Missing in Attention for Video Understanding | ✓ Link | 84.2 | RSANet-R50 (16 frames, ImageNet pretrained, a single clip) | 2021-11-02 |
| Temporal Query Networks for Fine-grained Video Understanding | | 81.8 | TQN | 2021-04-19 |
| PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition | ✓ Link | 81.3 | PMI Sampler | 2023-04-14 |
| Is Space-Time Attention All You Need for Video Understanding? | ✓ Link | 81 | TimeSformer-L | 2021-02-09 |
| Is Space-Time Attention All You Need for Video Understanding? | ✓ Link | 78 | TimeSformer-HR | 2021-02-09 |
| SlowFast Networks for Video Recognition | ✓ Link | 77.6 | SlowFast | 2018-12-10 |
| Is Space-Time Attention All You Need for Video Understanding? | ✓ Link | 75 | TimeSformer | 2021-02-09 |