Metric: GFLOPs (higher is better)
| # | Model↕ | GFLOPs▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | InternVideo2-6B | 13321 | Yes | InternVideo2: Scaling Foundation Models for Mult... | 2024-03-22 | Code |
| 2 | ST-Adapter (ViT-L, CLIP) | 8248 | Yes | ST-Adapter: Parameter-Efficient Image-to-Video T... | 2022-06-27 | Code |
| 3 | UniFormerV2-L | 5154 | Yes | - | - | Code |
| 4 | CT-Net Ensemble (R50, 8+12+16+24) | 280 | Yes | CT-Net: Channel Tensorization Network for Video ... | 2021-06-03 | Code |
| 5 | GC-TDN Ensemble (R50,8+16) | 110.1 | Yes | Group Contextualization for Video Recognition | 2022-03-18 | Code |
| 6 | E3D-L | 18.3 | No | Maximizing Spatio-Temporal Entropy of Deep 3D CN... | 2023-03-05 | Code |