VideoRefer
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Referring | VideoRefer-Bench-D | SC4.92 | 23 | |
| Video Understanding | VideoRefer-BenchQ | Overall Accuracy78.3 | 22 | |
| Region Captioning | VideoRefer-D (test) | Average Score3.68 | 16 |
Showing 3 of 3 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Referring | VideoRefer-Bench-D | SC4.92 | 23 | |
| Video Understanding | VideoRefer-BenchQ | Overall Accuracy78.3 | 22 | |
| Region Captioning | VideoRefer-D (test) | Average Score3.68 | 16 |