Metric: Average Accuracy (higher is better)
| # | Model↕ | Average Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | LaViLa (Finetuned, TimeSformer-L) | 81.75 | No | Learning Video Representations from Large Langua... | 2022-12-08 | Code |
| 2 | Min et al. | 69.58 | No | Integrating Human Gaze into Attention for Egocen... | 2020-11-08 | Code |
| 3 | GC-TSM | 65.1 | No | Group Contextualization for Video Recognition | 2022-03-18 | Code |
| 4 | SAP | 62.7 | No | Symbiotic Attention with Privileged Information ... | 2020-02-08 | - |
| 5 | LSTA | 61.9 | No | LSTA: Long Short-Term Attention for Egocentric A... | 2018-11-26 | Code |
| 6 | Ego-RNN | 60.8 | No | Attention is All We Need: Nailing Down Object-ce... | 2018-07-31 | Code |