Question Answering on LongVideoBench Medium Text-Related Perception
62.07AccuracyGPT4o+VSI
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT4o+VSIFrame=82025.08 | 62.07 | |
| GPT4oFrame=82025.08 | 48.28 | |
| GPT4o+TSTARFrame=82025.08 | 48.28 | |
| GPT4o+VSLSFrame=82025.08 | 48.28 | |
| GPT4o+SUBFrame=82025.08 | 46.55 |