| Paper | Code | Direct | ModelName | ReleaseDate |
|---|---|---|---|---|
| EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone | ✓ Link | 46.26 | EgoVLPv2 | 2023-07-11 |
| Glance and Focus: Memory Prompting for Multi-Event Video Question Answering | ✓ Link | 44.27 | GF(sup) | 2024-01-03 |
| Glance and Focus: Memory Prompting for Multi-Event Video Question Answering | ✓ Link | 43.06 | GF(uns) | 2024-01-03 |
| Egocentric Video-Language Pretraining | ✓ Link | 42.51 | EgoVLP | 2022-06-03 |