| Paper | Code | Test Accuracy | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| []() | 44.8 | Aurora (ours, r=64) Aurora (ours, r=64) | |||
| Zero-Shot Video Question Answering via Frozen Bidirectional Language Models | ✓ Link | 0.470 | FrozenBiLM | 2022-06-16 | |
| Just Ask: Learning to Answer Questions from Millions of Narrated Videos | ✓ Link | 0.415 | Just Ask | 2020-12-01 | |
| Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning | ✓ Link | 0.35 | SSML | 2020-03-06 |