| Paper | Code | Top 1 Accuracy | Top 5 Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| InternVideo2: Scaling Foundation Models for Multimodal Video Understanding | ✓ Link | 97.0 | InternVideo2-6B | 2024-03-22 | |
| UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer | ✓ Link | 95.5 | 99.8 | UniFormerV2-L | 2022-09-22 |
| Learn to cycle: Time-consistent feature discovery for action recognition | ✓ Link | 84.33 | 96.85 | SRTG r(2+1)d-101 | 2020-06-15 |
| Learn to cycle: Time-consistent feature discovery for action recognition | ✓ Link | 83.77 | 96.56 | SRTG r(2+1)d-50 | 2020-06-15 |
| Learn to cycle: Time-consistent feature discovery for action recognition | ✓ Link | 81.66 | 96.33 | SRTG r3d-101 | 2020-06-15 |
| Learn to cycle: Time-consistent feature discovery for action recognition | ✓ Link | 80.39 | 94.27 | SRTG r(2+1)d-34 | 2020-06-15 |
| Learn to cycle: Time-consistent feature discovery for action recognition | ✓ Link | 80.36 | 95.55 | SRTG r3d-50 | 2020-06-15 |
| Learn to cycle: Time-consistent feature discovery for action recognition | ✓ Link | 78.60 | 93.57 | SRTG r3d-34 | 2020-06-15 |