Metric: Video hit@1 (higher is better)
| # | Model↕ | Video hit@1 ▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ip-CSN-152 (RGB) | 75.5 | No | Video Classification with Channel-Separated Conv... | 2019-04-04 | Code |
| 2 | ip-CSN-101 (RGB) | 74.9 | No | Video Classification with Channel-Separated Conv... | 2019-04-04 | Code |
| 3 | R[2+1]D-Two-Stream-32frame | 73.3 | No | A Closer Look at Spatiotemporal Convolutions for... | 2017-11-30 | Code |
| 4 | R[2+1]D-RGB-32frame | 73 | No | A Closer Look at Spatiotemporal Convolutions for... | 2017-11-30 | Code |
| 5 | Conv pooling | 71.7 | No | Beyond Short Snippets: Deep Networks for Video C... | 2015-03-31 | Code |
| 6 | R[2+1]D-Flow-32frame | 68.4 | No | A Closer Look at Spatiotemporal Convolutions for... | 2017-11-30 | Code |
| 7 | P3D | 66.4 | No | Learning Spatio-Temporal Representation with Pse... | 2017-11-28 | Code |
| 8 | C3D | 61.1 | No | Learning Spatiotemporal Features with 3D Convolu... | 2014-12-02 | Code |
| 9 | DeepVideo’s Slow Fusion | 60.9 | No | - | - | Code |