Video on Toyota Smarthome dataset
Metric: CS (higher is better)
Metric: CS (higher is better)
| # | Model↕ | CS▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | π-ViT | 72.9 | Yes | Just Add $π$! Pose Induced Video Transformers fo... | 2023-11-30 | Code |
| 2 | EPAM-Net | 71.7 | Yes | EPAM-Net: An Efficient Pose-driven Attention-gui... | 2024-08-10 | Code |
| 3 | MMNet | 70.1 | Yes | - | - | Code |
| 4 | UNIK | 64.3 | No | UNIK: A Unified Framework for Real-world Skeleto... | 2021-07-19 | Code |
| 5 | AssembleNet++ | 63.6 | No | AssembleNet++: Assembling Modality Representatio... | 2020-08-18 | Code |
| 6 | AIRStreams | 62.11 | No | Adaptive Intermediate Representations for Video ... | 2021-04-14 | - |
| 7 | VPN (RGB + Pose) | 60.8 | Yes | VPN: Learning Video-Pose Embedding for Activitie... | 2020-07-06 | Code |
| 8 | Separable STA (RGB + Pose) | 54.2 | Yes | - | - | - |
| 9 | I3D + Non Local | 53.6 | Yes | Non-local Neural Networks | 2017-11-21 | Code |
| 10 | I3D | 53.4 | Yes | Quo Vadis, Action Recognition? A New Model and t... | 2017-05-22 | Code |
| 11 | Dense Trajectories | 41.9 | No | Improved Dense Trajectory with Cross Streams | 2016-04-29 | - |