Video on Toyota Smarthome dataset
Metric: CV1 (higher is better)
Metric: CV1 (higher is better)
| # | Model↕ | CV1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | π-ViT | 55.2 | Yes | Just Add $π$! Pose Induced Video Transformers fo... | 2023-11-30 | Code |
| 2 | VPN (RGB + Pose) | 43.8 | Yes | VPN: Learning Video-Pose Embedding for Activitie... | 2020-07-06 | Code |
| 3 | NPL | 39.6 | No | Recognizing Actions in Videos from Unseen Viewpo... | 2021-03-30 | - |
| 4 | UNIK | 36.1 | No | UNIK: A Unified Framework for Real-world Skeleto... | 2021-07-19 | Code |
| 5 | Separable STA (RGB + Pose) | 35.2 | Yes | - | - | - |
| 6 | I3D | 34.9 | Yes | Quo Vadis, Action Recognition? A New Model and t... | 2017-05-22 | Code |
| 7 | I3D + Non Local | 34.3 | Yes | Non-local Neural Networks | 2017-11-21 | Code |
| 8 | Dense Trajectories | 20.9 | No | Improved Dense Trajectory with Cross Streams | 2016-04-29 | - |