Keyframe Search on LongVideoBench Text-Related Perception Subsets
45AccuracyGPT4o+VSI
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT4o+VSIFrame=82025.08 | 45 | |
| GPT4o+TSTARFrame=82025.08 | 29.48 | |
| GPT4o+VSLSFrame=82025.08 | 27.17 |
| Method | Links | |
|---|---|---|
| GPT4o+VSIFrame=82025.08 | 45 | |
| GPT4o+TSTARFrame=82025.08 | 29.48 | |
| GPT4o+VSLSFrame=82025.08 | 27.17 |