| Paper | Code | With Audio (Acc %) | Without Audio (Acc %) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| PACS: A Dataset for Physical Audiovisual CommonSense Reasoning | ✓ Link | 96.3 ± 2.1 | 90.5 ± 3.1 | Human | 2022-03-21 |
| PACS: A Dataset for Physical Audiovisual CommonSense Reasoning | ✓ Link | 70.1 ± 1.0 | 68.4 ± 0.7 | Merlot Reserve (Large) | 2022-03-21 |
| PACS: A Dataset for Physical Audiovisual CommonSense Reasoning | ✓ Link | 60.0 ± 0.9 | 56.3 ± 0.7 | CLIP/AudioCLIP | 2022-03-21 |
| PACS: A Dataset for Physical Audiovisual CommonSense Reasoning | ✓ Link | 55.0 ± 1.1 | 52.5 ± 1.6 | Late Fusion | 2022-03-21 |
| PACS: A Dataset for Physical Audiovisual CommonSense Reasoning | ✓ Link | 50.4 | 50.4 | Majority | 2022-03-21 |
| PACS: A Dataset for Physical Audiovisual CommonSense Reasoning | ✓ Link | 60.6 ± 2.2 | UNITER (Large) | 2022-03-21 |