Star
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Oriented Object Detection | STAR (test) | AP39.45 | 60 | |
| Video Question Answering | STAR (test) | Interaction Score79.1 | 54 | |
| Video-based Question Answering | STAR | Accuracy78.6 | 50 | |
| Task#1 | STAR | Accuracy99.88 | 33 | |
| MAP Inference | STAR-dataset | Runtime0.02 | 25 | |
| Video Question Answering | STAR (val) | Mean Score63.8 | 22 | |
| Video Reasoning | STAR | Score67.7 | 19 | |
| Astronomical Super-resolution | STAR | PSNR34.66 | 16 | |
| Oriented Object Detection | STAR | AP5028.1 | 13 | |
| Task#5 | STAR | Score82.66 | 12 | |
| Statement Ranking | StaR Sports | Precision@55.547 | 12 | |
| Statement Ranking | StaR Beauty | Precision@56.2 | 12 | |
| Statement Ranking | StaR Clothes | Precision@515.136 | 12 | |
| Statement Ranking | StaR Toys | Precision@56.309 | 12 | |
| Selective Regression | star (test) | Conditional Large-Loss Rate28.5 | 12 | |
| Object Detection | STAR | AP (Car)14.5 | 11 | |
| Video Question Answering | STAR v1.0 (test) | Interaction Accuracy73.7 | 10 | |
| Video Question Answering | STAR V (test) | Accuracy42.8 | 10 | |
| Conformal Prediction | star | MC (%)91.82 | 8 | |
| Task-Oriented Dialogue | STAR | F1 Score68 | 7 | |
| Video Understanding | STAR | Score58.77 | 7 | |
| Regression | star (test) | Marginal Coverage91 | 7 | |
| Regression | star 2161 (test outliers) | Mean Outlier Coverage88 | 7 | |
| Regression | star | SMIS11.33 | 7 | |
| Regression | star n=2161 (test) | ILR1 | 7 |
Showing 25 of 41 rows